© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2869
    Prev
    Next
    INDEX
    Explanations

    anonymous tips, feedback, surfing, or sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èIJ¥
    -0.09
     Piece
    -0.08
    èĻIJ
    -0.08
     Pri
    -0.08
    çijĻ
    -0.08
     Saw
    -0.07
     Hats
    -0.07
    å¸ĮæľĽèĥ½å¤Ł
    -0.07
    roe
    -0.07
    æĽ
    -0.07
    POSITIVE LOGITS
    ãģ¤ãģį
    0.10
    ’B
    0.10
    åıĹ访
    0.09
    zed
    0.09
     khá»ıi
    0.09
    _bd
    0.09
    æłijæŀĿ
    0.09
     luáºŃn
    0.08
    éĥ¡
    0.08
    èĽŁ
    0.08
    Activations Density 0.006%

    No Known Activations