© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21280
    Prev
    Next
    INDEX
    Explanations

    creators and companies

    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
    篮
    -0.09
     kiá»ĩn
    -0.09
    eded
    -0.09
    sing
    -0.09
    worth
    -0.08
    kick
    -0.08
    ä¸ĭæĿ¥çļĦ
    -0.08
    ACP
    -0.08
    èĦı
    -0.08
    çľĭæ³ķ
    -0.08
    POSITIVE LOGITS
    leine
    0.13
    iliar
    0.10
    ../../../
    0.10
    0.10
    abbrev
    0.10
    esch
    0.10
    uilt
    0.09
    hev
    0.09
    avana
    0.09
    ç£ĭ
    0.09
    Activations Density 0.025%

    No Known Activations