© 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. 34045
    Prev
    Next
    INDEX
    Explanations

    think about

    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
    /on
    -0.10
    é£İæĻ¯
    -0.09
    written
    -0.09
    eda
    -0.09
    æĻ¯èī²
    -0.08
    /from
    -0.08
    æĢĿæĥ³
    -0.08
    å°ıå¿ĥ
    -0.08
    TL
    -0.08
    mtime
    -0.08
    POSITIVE LOGITS
    adel
    0.11
    è¿Ļåħ¶ä¸Ń
    0.09
    _lb
    0.09
    åĩłåįģå¹´
    0.09
    acle
    0.09
    olist
    0.09
    oren
    0.09
    è´¨éĩı管çIJĨ
    0.08
    æ¸ħæ¥ļ
    0.08
    =utf
    0.08
    Activations Density 0.019%

    No Known Activations