© 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. 62655
    Prev
    Next
    INDEX
    Explanations

    statistical leaders or numbers

    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
    å²Ĺ
    -0.09
    .contents
    -0.09
    frage
    -0.09
    isor
    -0.08
    .runner
    -0.08
    çģĮ
    -0.08
    Iso
    -0.08
    eti
    -0.08
    uhan
    -0.08
    Helmet
    -0.08
    POSITIVE LOGITS
    ä¸ļ绩
    0.12
     trông
    0.11
     statistics
    0.10
    ç»Łè®¡
    0.10
    èľľ
    0.10
     stats
    0.10
     Äijỡ
    0.10
     optics
    0.09
    è¹Ĭ
    0.09
    ç»Łè®¡æķ°æį®
    0.09
    Activations Density 0.009%

    No Known Activations