© 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. 55094
    Prev
    Next
    INDEX
    Explanations

    english us

    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
    饶
    -0.09
    types
    -0.08
    ione
    -0.08
    _Tab
    -0.08
    èģĺ
    -0.08
    achs
    -0.08
    .annot
    -0.08
    éĻ´
    -0.08
    ลม
    -0.08
    anus
    -0.08
    POSITIVE LOGITS
    .wikipedia
    0.09
    åİķ
    0.09
    coming
    0.09
    æ¸İ
    0.09
    umpy
    0.08
    ×Ļ×Ķ
    0.08
    ç»·
    0.08
    ÑĢÑĥÑģ
    0.08
    æĸ°åĵģ
    0.08
    -US
    0.08
    Activations Density 0.108%

    No Known Activations