© 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. 22661
    Prev
    Next
    INDEX
    Explanations

    sizes (big, small, large)

    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
    ä¸įå°½
    -0.09
    大åĨĽ
    -0.09
    amen
    -0.09
    è°ħ
    -0.08
    å°ıåĮº
    -0.08
    大åİħ
    -0.08
    大éģĵ
    -0.08
     doubled
    -0.08
    ä¸įå®Į
    -0.08
    .openg
    -0.08
    POSITIVE LOGITS
    /small
    0.12
    _ENDIAN
    0.11
    -scale
    0.11
    -sized
    0.10
    /big
    0.10
    æ¿©
    0.10
    itarian
    0.10
    ä¸įå°ı
    0.10
    éķĽ
    0.10
    éŨæĪ·
    0.10
    Activations Density 0.121%

    No Known Activations