© 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. 33955
    Prev
    Next
    INDEX
    Explanations

    at your option

    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
    åįļ
    -0.10
    纯æ´ģ
    -0.09
     Ded
    -0.09
    atus
    -0.09
    à¹Ĥà¸ļ
    -0.09
    æĴŃ
    -0.09
    ä¸Ģå¿ĥ
    -0.09
    usat
    -0.08
    ideal
    -0.08
    æĩĤäºĭ
    -0.08
    POSITIVE LOGITS
    è´
    0.10
    ong
    0.09
    æ°Ķæ°Ľ
    0.09
    é«ĺåİŁ
    0.09
    andan
    0.09
    èĽ²
    0.09
    æģ¹
    0.09
    æ¼ķ
    0.09
    çijľ
    0.08
    ifen
    0.08
    Activations Density 0.017%

    No Known Activations