© 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. 55870
    Prev
    Next
    INDEX
    Explanations

    flaking off, desquamation, psoriasis

    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
    ç¼ļ
    -0.09
    _FM
    -0.09
    ista
    -0.09
    izon
    -0.08
    áng
    -0.08
    draft
    -0.08
    æĥ®
    -0.08
    ised
    -0.08
    åĬ©çIJĨ
    -0.08
    é£İæļ´
    -0.08
    POSITIVE LOGITS
    åĦ¿
    0.14
    åħĴ
    0.11
    磶
    0.10
    累累
    0.10
    peare
    0.09
    åŃIJéĩĮ
    0.09
    kel
    0.09
    rang
    0.09
    ⼦
    0.09
    åīįèĢħ
    0.09
    Activations Density 0.017%

    No Known Activations