© 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. 7-RESID-POST-AA
    11. 38227
    Prev
    Next
    INDEX
    Explanations

    Russian language code

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    を迎
    -0.08
     предостав
    -0.07
    挑战
    -0.07
    诉
    -0.07
    ’int
    -0.07
    elin
    -0.07
     challenging
    -0.07
    稀缺
    -0.07
    .repeat
    -0.07
    قدم
    -0.07
    POSITIVE LOGITS
    剀
    0.08
    PNG
    0.07
    وها
    0.07
     postal
    0.07
    _normalize
    0.07
     הפי
    0.07
    _document
    0.07
    icks
    0.07
     dreamed
    0.07
    ומות
    0.07
    Activations Density 0.001%

    No Known Activations