© 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. 32906
    Prev
    Next
    INDEX
    Explanations

    open house registration

    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
    åģıå·®
    -0.09
     Sue
    -0.08
    æĥ³åĪ°
    -0.08
    æ¦Ķ
    -0.08
    åİĮ
    -0.08
    纵åIJij
    -0.08
    æ²»
    -0.08
    æĪijèĩªå·±
    -0.08
     Gang
    -0.08
    带åĬ¨
    -0.07
    POSITIVE LOGITS
    é¡·
    0.10
    .Scheme
    0.10
    è¿ŀéĶģ
    0.09
    èĬ¬
    0.09
     Vac
    0.09
    ictionaries
    0.09
    ico
    0.09
    åĭ¿
    0.09
    acas
    0.09
    èĩªçĦ¶çķĮ
    0.09
    Activations Density 0.044%

    No Known Activations