© 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. 50144
    Prev
    Next
    INDEX
    Explanations

    Levine Bridgewater Ibrahim College

    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
    èĮ
    -0.10
    骢
    -0.09
    sticks
    -0.09
    stä
    -0.09
    æĨ§æĨ¬
    -0.08
    оÑĦ
    -0.08
    éĤ¨
    -0.08
    å´´
    -0.08
     Angelo
    -0.08
    SSERT
    -0.08
    POSITIVE LOGITS
    alem
    0.12
    ãģĹãģĭãģªãģĦ
    0.10
    è´£
    0.09
    .Restr
    0.09
    .opend
    0.09
    vement
    0.08
    æµģæ°´
    0.08
    弩
    0.08
     sap
    0.08
    æĬľ
    0.08
    Activations Density 0.004%

    No Known Activations