© 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. 21537
    Prev
    Next
    INDEX
    Explanations

    donating or donated

    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
    客æĪ·éľĢæ±Ĥ
    -0.10
    grass
    -0.10
    engers
    -0.09
    é¢Ħå®ļ
    -0.09
     dps
    -0.09
    çIJ¶
    -0.08
    _FORWARD
    -0.08
    romatic
    -0.08
    bus
    -0.08
    uit
    -0.08
    POSITIVE LOGITS
    ãn
    0.09
    ä¸İä¼Ĺ
    0.09
    èĩ³æѤ
    0.09
     kepada
    0.09
    ux
    0.08
    åĵij
    0.08
    åĴĮæĶ¯æĮģ
    0.08
    plx
    0.08
    _fmt
    0.08
    zed
    0.08
    Activations Density 0.019%

    No Known Activations