© 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. 32418
    Prev
    Next
    INDEX
    Explanations

    operated by

    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
    oted
    -0.09
    roof
    -0.09
    ifier
    -0.09
    æľ¬ç«Ļ
    -0.09
    åı£æ°´
    -0.09
     Gardner
    -0.08
    ÑģÑĤÑĢÑĥкÑĤоÑĢ
    -0.08
    æī¾å·¥ä½ľ
    -0.08
    _surf
    -0.08
    èħ¥
    -0.08
    POSITIVE LOGITS
    engl
    0.11
    ivia
    0.10
    èĢħçļĦ
    0.09
    ¨
    0.09
    ERS
    0.09
    plier
    0.09
    ozilla
    0.09
    иÑĤел
    0.09
    ating
    0.09
    MENT
    0.08
    Activations Density 0.045%

    No Known Activations