© 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. 48624
    Prev
    Next
    INDEX
    Explanations

    overhead supply

    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
    ä»İä¸Ń
    -0.10
    åIJģ
    -0.10
     Caldwell
    -0.10
    .LA
    -0.09
     alien
    -0.09
    masters
    -0.09
    ä¸Ģ大
    -0.09
    nants
    -0.09
    çªĿ
    -0.09
    lient
    -0.09
    POSITIVE LOGITS
    åĨ²åĩ»
    0.10
    æĢ¥
    0.10
    çŁŃæľŁ
    0.10
    åĪ·
    0.09
    åĨ³çŃĸ
    0.09
    quate
    0.09
    æĹ¥åĨħ
    0.09
    éĨĴæĿ¥
    0.08
    ä¸Ĭä¸ĭ
    0.08
    Morning
    0.08
    Activations Density 0.038%

    No Known Activations