© 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. 56188
    Prev
    Next
    INDEX
    Explanations

    MTV, MGM, MIT, ACM identifiers

    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
    ouble
    -0.08
    ãĤ£
    -0.08
    uming
    -0.08
    iton
    -0.08
    quet
    -0.08
    åĮ¯
    -0.08
    anmar
    -0.08
    ìĦĿ
    -0.07
    acre
    -0.07
    ç§ijåĪĽ
    -0.07
    POSITIVE LOGITS
    èĨı
    0.11
    æ»ĵ
    0.09
    ypy
    0.09
    ç¾Ķ
    0.09
    สà¸Ķ
    0.08
    èĽ¤
    0.08
    allon
    0.08
     ÑĢож
    0.08
    å¿ħè¦ģçļĦ
    0.08
    rees
    0.08
    Activations Density 0.006%

    No Known Activations