© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21372
    Prev
    Next
    INDEX
    Explanations

    documentation, Log, repeat, Link

    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
     Coc
    -0.08
    à¹Ģà¸Ĺ
    -0.08
    coc
    -0.08
    Servlet
    -0.08
    åı·ç§°
    -0.08
    opp
    -0.08
    åģļ大åģļ强
    -0.08
    å®ħ
    -0.08
     Geek
    -0.07
    ġ
    -0.07
    POSITIVE LOGITS
    ativity
    0.10
    .nih
    0.10
    èij³
    0.10
    é«ĺåħ´
    0.10
    å¾·æĭī
    0.09
    drs
    0.09
     Princip
    0.09
    ä¸įæĢķ
    0.09
    ultz
    0.09
    殪
    0.09
    Activations Density 0.165%

    No Known Activations