© 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. 71036
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    “And
    -0.08
     butcher
    -0.07
    _OTHER
    -0.07
    ,and
    -0.07
    _super
    -0.07
    "And
    -0.07
    STORE
    -0.07
     insure
    -0.07
    Wild
    -0.07
     suas
    -0.07
    POSITIVE LOGITS
    已达
    0.08
     triang
    0.07
    జ
    0.07
    *)↵
    0.07
     unchanged
    0.07
    loh
    0.07
    etto
    0.07
    החלטה
    0.07
    𝑊
    0.07
     пара
    0.07
    Activations Density 0.002%

    No Known Activations