© 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. 38922
    Prev
    Next
    INDEX
    Explanations

    hair loss alopecia

    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
    å¤ĸæı´
    -0.09
    ResponseBody
    -0.09
    ieber
    -0.09
     rÃłng
    -0.09
    æĥij
    -0.09
     tract
    -0.09
    áĢĬ
    -0.09
    èĤĮ
    -0.08
    ç»°
    -0.08
    @qq
    -0.08
    POSITIVE LOGITS
    æ®ī
    0.11
    ç§ĥ
    0.10
    å°ī
    0.10
    好äºĭ
    0.09
    Acceler
    0.09
    pecia
    0.09
    çĻ½æĸij
    0.09
    èĢ·
    0.08
    åĭº
    0.08
    产ä¸ļéĽĨèģļ
    0.08
    Activations Density 0.044%

    No Known Activations