© 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. 58090
    Prev
    Next
    INDEX
    Explanations

    defendant

    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
    nda
    -0.11
    èħ¥
    -0.09
    人寿
    -0.09
    ãģ£ãģįãĤĬ
    -0.09
    thon
    -0.09
    èĢ»
    -0.09
    å¯Įæ°ij
    -0.08
    flix
    -0.08
    il
    -0.08
    æł·çļĦ
    -0.08
    POSITIVE LOGITS
    sWith
    0.11
    /or
    0.11
    们çļĦ
    0.10
    ry
    0.10
    /respond
    0.09
    RAD
    0.09
    ideo
    0.09
    zeit
    0.09
    REN
    0.09
    们
    0.09
    Activations Density 0.078%

    No Known Activations