© 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. 21316
    Prev
    Next
    INDEX
    Explanations

    get out of

    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
    åī½
    -0.10
    views
    -0.09
    probe
    -0.09
    ä¸įåIJĮç¨ĭ度
    -0.09
     Probe
    -0.09
    éĴĹ
    -0.09
    æĢ§å¼º
    -0.08
    æ·¡åĮĸ
    -0.08
     tess
    -0.08
    ithe
    -0.08
    POSITIVE LOGITS
    /respond
    0.12
    åĽ°å¢ĥ
    0.11
    æĿŁç¼ļ
    0.11
    CLA
    0.09
     завиÑģ
    0.09
    deps
    0.09
    çİ°çĬ¶
    0.09
    .scrollTo
    0.08
    æ¯Ĵ
    0.08
    .LAZY
    0.08
    Activations Density 0.034%

    No Known Activations