© 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. 18636
    Prev
    Next
    INDEX
    Explanations

    what how who

    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
    ndo
    -0.10
    atcher
    -0.10
    uala
    -0.09
    .nan
    -0.09
    bsub
    -0.08
    CLE
    -0.08
    èµŃ
    -0.08
    alth
    -0.08
    dam
    -0.08
    abal
    -0.08
    POSITIVE LOGITS
    ibri
    0.10
    ä¸ĢæĿ¡é¾Ļ
    0.09
    ä¸Ģç«Ļ
    0.09
    æĿľåħ°
    0.09
    ä¸Ģæ±½
    0.09
    æ¡£
    0.09
    _ALLOC
    0.09
    æijĺç¼ĸ
    0.08
    æŀ¸
    0.08
    è°ģçŁ¥éģĵ
    0.08
    Activations Density 0.037%

    No Known Activations