© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 80008
    Prev
    Next
    INDEX
    Explanations

    English

    np_max-act · gemini-2.0-flash

    mentions of the English language, especially as a subject/label or in discussions of language proficiency and instruction.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    @Id
    -0.08
    network
    -0.07
     Aer
    -0.07
    �
    -0.07
    推动
    -0.07
    �
    -0.07
     CC
    -0.07
    客房
    -0.07
    阀
    -0.07
    (Encoding
    -0.07
    POSITIVE LOGITS
    Alias
    0.07
     English
    0.07
    słuch
    0.07
    .Qual
    0.07
    市级
    0.07
    全国人民
    0.07
     meats
    0.07
    Franc
    0.06
     trash
    0.06
     Prostit
    0.06
    Activations Density 0.019%

    No Known Activations