© 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. 3379
    Prev
    Next
    INDEX
    Explanations

    Software instructions

    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
    pname
    -0.07
    硇
    -0.07
    استف
    -0.07
    PAGE
    -0.07
    [arr
    -0.07
    ificador
    -0.07
    :result
    -0.06
    ycler
    -0.06
    댤
    -0.06
    㹦
    -0.06
    POSITIVE LOGITS
     lips
    0.07
    ­s
    0.07
    ↵↵↵↵↵↵↵↵↵↵
    0.07
    <|im_end|>
    0.07
    Observ
    0.07
    SQLite
    0.07
     urgent
    0.07
     eyeb
    0.07
     Dashboard
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    Activations Density 0.028%

    No Known Activations