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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 25662
    Prev
    Next
    INDEX
    Explanations

    Pol

    np_max-act · gemini-2.0-flash
    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
    3
    -0.07
    diet
    -0.07
    交谈
    -0.07
    lien
    -0.07
    ILL
    -0.07
     Singh
    -0.07
    iked
    -0.07
    宣传片
    -0.07
    不成
    -0.07
    amm
    -0.07
    POSITIVE LOGITS
     karde
    0.07
    എ
    0.07
     denotes
    0.06
    ility
    0.06
    จำก
    0.06
     pol
    0.06
     деят
    0.06
     niekt
    0.06
     prv
    0.06
    BaseContext
    0.06
    Activations Density 0.012%

    No Known Activations