© 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. 81782
    Prev
    Next
    INDEX
    Explanations

    would

    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
    _clr
    -0.07
    _chi
    -0.06
     mh
    -0.06
    (md
    -0.06
    iVar
    -0.06
    熊
    -0.06
    (tt
    -0.06
     resembl
    -0.06
    当你
    -0.06
    簡�
    -0.06
    POSITIVE LOGITS
    实在是
    0.09
    的重要性
    0.08
    。”↵↵
    0.08
    }}↵↵
    0.07
     workspace
    0.07
     figure
    0.07
     verfügbar
    0.07
    >;
↵
    0.07
    .).
    0.07
    led
    0.07
    Activations Density 0.007%

    No Known Activations