© 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. 62560
    Prev
    Next
    INDEX
    Explanations

    company or organization names

    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
    ites
    -0.09
     kitty
    -0.09
    ously
    -0.09
    fos
    -0.09
    æ»Ĥ
    -0.09
    _paint
    -0.08
    pleted
    -0.08
    SelectedItem
    -0.08
    _JUMP
    -0.08
    jd
    -0.08
    POSITIVE LOGITS
    åĥ®
    0.10
    è°ĥåij³
    0.10
    åľ¨è¿ĩ渡
    0.09
    溲
    0.09
    èĩ¾
    0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    0.09
     Duffy
    0.09
    è¿Ļç¯ĩæĸĩç«ł
    0.09
     Tavern
    0.09
    æĸŃ
    0.09
    Activations Density 0.199%

    No Known Activations