© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52485
    Prev
    Next
    INDEX
    Explanations

    years

    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
    æĭIJ
    -0.11
    èĦĸåŃIJ
    -0.10
    çģµåĬ¨
    -0.10
    icious
    -0.09
    avec
    -0.09
    å¾ĺå¾Ĭ
    -0.09
    港澳
    -0.09
    ä¸į代表
    -0.09
    ç½ijéĢļ
    -0.09
    ÑĢÑĥд
    -0.09
    POSITIVE LOGITS
    æķ¢
    0.09
     Hoy
    0.08
     tape
    0.08
    _TB
    0.08
    bart
    0.08
    æĶĴ
    0.07
    访
    0.07
    Wilson
    0.07
     instant
    0.07
    è¿Ļç¬Ķ
    0.07
    Activations Density 0.152%

    No Known Activations