© 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. 30069
    Prev
    Next
    INDEX
    Explanations

    Pokémon

    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
     전혀
    -0.09
     Signature
    -0.07
    -that
    -0.07
    נים
    -0.07
    奔跑
    -0.07
     Diploma
    -0.07
     Symbols
    -0.07
    يم
    -0.07
     Fres
    -0.07
     וגם
    -0.07
    POSITIVE LOGITS
    consult
    0.07
    Runtime
    0.07
    Carol
    0.07
    按下
    0.07
    _sk
    0.06
    >');
↵
    0.06
    Unsafe
    0.06
    cpu
    0.06
    Visual
    0.06
    Deal
    0.06
    Activations Density 0.016%

    No Known Activations