© 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. 27347
    Prev
    Next
    INDEX
    Explanations

    fusion

    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
    stairs
    -0.10
    rus
    -0.10
    ÙĪاس
    -0.09
    amar
    -0.09
    ç±į
    -0.09
    ter
    -0.08
    agan
    -0.08
    ton
    -0.08
    upo
    -0.08
     NotImplemented
    -0.08
    POSITIVE LOGITS
    ibly
    0.11
    åľ¨ä¸Ģèµ·
    0.11
    itarian
    0.10
    ible
    0.10
    illez
    0.09
    è´¯éĢļ
    0.09
    èŀįåIJĪ
    0.09
    åijĬ
    0.09
    çīĪæĿĥ声æĺİ
    0.09
    iator
    0.09
    Activations Density 0.051%

    No Known Activations