© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36504
    Prev
    Next
    INDEX
    Explanations

    systemic/topical treatments or medication

    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
    addy
    -0.09
    .setWindowTitle
    -0.09
    åħ¥åºĵ
    -0.08
    wyn
    -0.08
    åıĪæĺ¯
    -0.08
    fty
    -0.08
     Panama
    -0.08
    iri
    -0.08
     Zot
    -0.08
     knocked
    -0.08
    POSITIVE LOGITS
    èĭij
    0.10
    æħķ
    0.09
    褥
    0.09
    åijĬè¯īä»ĸ
    0.09
    åIJijçĿĢ
    0.09
    æĹŃ
    0.09
    ulative
    0.09
    é¹Ħ
    0.09
    etas
    0.08
    ivar
    0.08
    Activations Density 0.175%

    No Known Activations