© 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. 50482
    Prev
    Next
    INDEX
    Explanations

    sports coach and equipment

    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
    èĦ±ç¦»
    -0.10
    æĮĤéĴ©
    -0.10
    washer
    -0.10
    à°³
    -0.10
    .ErrorMessage
    -0.10
    gression
    -0.10
    LError
    -0.10
    çĽ¸å·®
    -0.09
     AraÅŁtırma
    -0.09
     moż
    -0.09
    POSITIVE LOGITS
    æ£ł
    0.09
     Fan
    0.08
    4
    0.08
    5
    0.08
    2
    0.08
    éĵ¨
    0.08
     ir
    0.08
    (admin
    0.08
    8
    0.08
    uml
    0.08
    Activations Density 0.197%

    No Known Activations