© 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. 36224
    Prev
    Next
    INDEX
    Explanations

    inky Boots

    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
    anford
    -0.10
    å¨ĺå¨ĺ
    -0.09
    gies
    -0.09
    wyn
    -0.09
    åıijå±ķåīįæĻ¯
    -0.09
    åŃIJéĩĮ
    -0.09
    tery
    -0.09
    inary
    -0.09
    æ®
    -0.09
    lements
    -0.09
    POSITIVE LOGITS
    edly
    0.09
    elope
    0.09
     trouble
    0.09
    leton
    0.09
    prises
    0.09
    pad
    0.09
    ering
    0.09
    alité
    0.09
    ERM
    0.09
    ovation
    0.09
    Activations Density 0.053%

    No Known Activations