© 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. 54491
    Prev
    Next
    INDEX
    Explanations

    'p' followed by non-alphanumeric or specific code

    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
    eri
    -0.09
    lim
    -0.08
    åIJįçīĮ
    -0.08
    orns
    -0.08
    å¥ī
    -0.08
    oire
    -0.08
    å¥ĭ
    -0.08
    éĴĹ
    -0.08
    微信群
    -0.07
    表æ¼Ķ
    -0.07
    POSITIVE LOGITS
    [input
    0.09
    离
    0.09
    омн
    0.09
    зн
    0.09
    .dt
    0.09
    èĻ®
    0.09
    çģ«
    0.09
    apo
    0.09
    éĶ¦ç»£
    0.09
    第ä¸ĢæĿ¡
    0.09
    Activations Density 0.120%

    No Known Activations