© 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. 34953
    Prev
    Next
    INDEX
    Explanations

    the itself

    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
    ess
    -0.10
    们
    -0.10
    客æĪ·æıIJä¾Ľ
    -0.10
    åı
    -0.09
    å°ıå§IJå§IJ
    -0.09
    fully
    -0.09
    ç»ĦåĽ¾
    -0.09
    hip
    -0.09
    innen
    -0.09
    åı¹
    -0.09
    POSITIVE LOGITS
    æ¸Ĺ
    0.09
    itial
    0.09
    ruz
    0.09
    ÑĤай
    0.09
    chy
    0.09
    ivar
    0.09
    rees
    0.08
    för
    0.08
    omore
    0.08
    ivet
    0.08
    Activations Density 0.013%

    No Known Activations