© 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. 62844
    Prev
    Next
    INDEX
    Explanations

    body parts and related products

    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
     haired
    -0.09
    GOP
    -0.09
    éĩĬæĶ¾
    -0.09
    /cop
    -0.09
    èľľèľĤ
    -0.09
    ðŁįİ
    -0.08
    åķĨåĬ¡
    -0.08
    -haired
    -0.08
     cigar
    -0.08
    HECK
    -0.08
    POSITIVE LOGITS
    åĻ¨
    0.09
    лаг
    0.09
    åīĤ
    0.09
    çĶ¨åĵģ
    0.08
    è¡¥
    0.08
     protection
    0.08
    èµĭ
    0.08
    仪
    0.08
    uko
    0.08
    urator
    0.08
    Activations Density 0.240%

    No Known Activations