© 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. 22749
    Prev
    Next
    INDEX
    Explanations

    HTTP request

    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
    ç±į
    -0.10
    mpr
    -0.08
    ä¸įå±ij
    -0.08
    èł¡
    -0.08
    aroo
    -0.08
    éģĹæĨ¾
    -0.08
    ernes
    -0.08
    rier
    -0.08
    dados
    -0.08
    æ£Ĵ
    -0.08
    POSITIVE LOGITS
    请æ±Ĥ
    0.11
    .Headers
    0.10
    .Http
    0.09
    FileType
    0.09
    lemn
    0.09
    .getRequest
    0.09
     请æ±Ĥ
    0.09
    .FILES
    0.09
     requests
    0.09
     request
    0.09
    Activations Density 0.539%

    No Known Activations