© 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. 5728
    Prev
    Next
    INDEX
    Explanations

    efficacy and outcomes

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.10
     лиÑĪÑĮ
    -0.10
    สà¸Ķ
    -0.09
     sheer
    -0.08
    à¸ĩ
    -0.08
     bunker
    -0.08
    .gnu
    -0.08
    à¸Ħà¸Ń
    -0.08
    LY
    -0.08
    .gwt
    -0.08
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.13
    Ùij
    0.10
    ê¹IJ
    0.09
    imestep
    0.09
    ıt
    0.09
    italize
    0.09
    erator
    0.09
    ald
    0.09
    erate
    0.09
    cul
    0.08
    Activations Density 0.559%

    No Known Activations