© 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. 49334
    Prev
    Next
    INDEX
    Explanations

    they are

    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
    微信åħ¬ä¼Ĺ
    -0.10
    她们
    -0.09
    Stamp
    -0.09
    Stamped
    -0.09
    ania
    -0.08
    åºĸ
    -0.08
    uem
    -0.08
    åħ¥
    -0.08
    æĸ¯é¡¿
    -0.08
    ç¼®
    -0.08
    POSITIVE LOGITS
    ghan
    0.09
    _ck
    0.09
    LineNumber
    0.08
    è°
    0.08
    ä»İä¸Ń
    0.08
    èħ°
    0.08
    devil
    0.08
     %-
    0.08
    Hosting
    0.08
    让å®ĥ
    0.08
    Activations Density 0.136%

    No Known Activations