© 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. 33843
    Prev
    Next
    INDEX
    Explanations

    command line arguments

    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
    æī¬
    -0.10
    kee
    -0.09
    >window
    -0.08
    à¹Ģà¸ĭ
    -0.08
    èµĦ
    -0.08
    /documentation
    -0.08
     Cly
    -0.08
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.08
    alk
    -0.08
    主æµģ
    -0.08
    POSITIVE LOGITS
    owie
    0.11
    usch
    0.09
    ëł¹
    0.09
    -border
    0.09
    unities
    0.09
    abez
    0.08
    亢
    0.08
    Ùħات
    0.08
    defaultValue
    0.08
    ç»Ī身
    0.08
    Activations Density 0.445%

    No Known Activations