© 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. 18904
    Prev
    Next
    INDEX
    Explanations

    nothing quite like

    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
    ibs
    -0.09
    ооÑĢÑĥж
    -0.09
    åħ«åŃĹ
    -0.09
    prov
    -0.09
     Dot
    -0.09
    /Grid
    -0.09
    åĭī强
    -0.09
    ç»Ī究
    -0.08
    Reuse
    -0.08
    æĮĩæľĽ
    -0.08
    POSITIVE LOGITS
    èĥĨ
    0.10
    åħ¶ä»ĸ
    0.09
    .other
    0.09
    other
    0.09
     Other
    0.09
     other
    0.08
    Other
    0.08
    å¹³åĩ¡
    0.08
    _other
    0.08
    indo
    0.08
    Activations Density 0.089%

    No Known Activations