© 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. 39837
    Prev
    Next
    INDEX
    Explanations

    mold, fungi, contamination

    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
    èĢĹ
    -0.10
    裤
    -0.10
     Elk
    -0.09
    èѦåĬ¡
    -0.09
    èĥ½èĢĹ
    -0.09
    gue
    -0.09
     rect
    -0.09
    opia
    -0.08
    nds
    -0.08
    ä¸ī大
    -0.08
    POSITIVE LOGITS
    åĢĴ
    0.11
    á»ĩn
    0.10
    å²ģæľĪ
    0.10
    å½±ä¸ļ
    0.09
     Dollar
    0.09
    åĮ£
    0.09
     Erg
    0.08
     mere
    0.08
    _stub
    0.08
    åŃ³
    0.08
    Activations Density 0.212%

    No Known Activations