© 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 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. 74701
    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
    公章
    -0.07
    ần
    -0.07
    渺
    -0.07
     manned
    -0.07
     hiện
    -0.06
    苍白
    -0.06
     автом
    -0.06
    气息
    -0.06
    חורף
    -0.06
    -sm
    -0.06
    POSITIVE LOGITS
     Subset
    0.07
     Schmidt
    0.07
     Nathan
    0.06
    ива
    0.06
    ‖
    0.06
    pleado
    0.06
    왤
    0.06
    ↵    ↵↵
    0.06
     pee
    0.06
    ---
    0.06
    Activations Density 0.051%

    No Known Activations