© 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. 6544
    Prev
    Next
    INDEX
    Explanations

    all the time

    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
    èĥ¥
    -0.11
    çļĦä¸ĢåĪĩ
    -0.09
    ç§įç§į
    -0.08
    è§Ĵ度æĿ¥çľĭ
    -0.08
    çĭĢ
    -0.08
    asso
    -0.08
    æ´ĭæ´ĭ
    -0.08
    èĦĸ
    -0.08
    äºİä¸Ģä½ĵ
    -0.08
    佯
    -0.08
    POSITIVE LOGITS
    å§Ķä¼ļ
    0.11
    æķ¬
    0.10
    ilers
    0.09
    çģ«èĬ±
    0.08
    èıł
    0.08
    serter
    0.08
    ulin
    0.08
     sÆ°
    0.08
    ilters
    0.08
    好人
    0.08
    Activations Density 0.009%

    No Known Activations