© 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. 57860
    Prev
    Next
    INDEX
    Explanations

    state university or state court

    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
    éĹªçĥģ
    -0.11
    isphere
    -0.11
    麻
    -0.10
    æĥ³åĥı
    -0.10
    è¯ļä¿¡
    -0.09
    ç«Ļèµ·æĿ¥
    -0.09
    âĴ¸
    -0.09
     useClass
    -0.09
    WARN
    -0.09
    群ä¼Ĺ
    -0.09
    POSITIVE LOGITS
    ingly
    0.09
    idth
    0.09
    diamond
    0.08
    å§Ķ
    0.08
    Difficulty
    0.08
    æŀķ
    0.08
    eg
    0.08
     недо
    0.08
    ens
    0.08
    ç«
    0.08
    Activations Density 0.004%

    No Known Activations