© 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. 55452
    Prev
    Next
    INDEX
    Explanations

    fuel cell

    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
    es
    -0.10
    纯æ´ģ
    -0.09
    æ¸
    -0.09
    ieur
    -0.09
    ãĥ¥
    -0.09
    å¯Ł
    -0.09
    IMER
    -0.09
    å±ģ
    -0.08
    osing
    -0.08
    icle
    -0.08
    POSITIVE LOGITS
    licit
    0.12
    led
    0.10
    änd
    0.10
    oenix
    0.09
    ä¸įåłª
    0.09
    licity
    0.09
    uet
    0.09
     Äijá»Ļ
    0.09
    ledged
    0.09
    erman
    0.09
    Activations Density 0.015%

    No Known Activations