© 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. 27169
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    aison
    -0.10
    秽
    -0.09
    åĩłå¼ł
    -0.09
    交ç»Ļ
    -0.08
    é£İè²Į
    -0.08
    rais
    -0.08
    使æĪij
    -0.08
    van
    -0.08
     Paw
    -0.08
    lew
    -0.08
    POSITIVE LOGITS
    è¿ĽæĿ¥
    0.10
    æł¸å¿ĥåĮº
    0.10
    éħIJ
    0.10
    æĿ¥è¿Ľè¡Į
    0.09
    iri
    0.09
    asu
    0.09
    åŃ¥
    0.09
    æ¶İ
    0.09
    å½Ģ
    0.09
    æł¸å¿ĥ
    0.09
    Activations Density 0.034%

    No Known Activations