© 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. 3788
    Prev
    Next
    INDEX
    Explanations

    not applicable / null values

    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
    UTION
    -0.10
    tim
    -0.09
    orris
    -0.08
     spree
    -0.08
    ÑģÑĤ
    -0.08
    ports
    -0.08
    åĪļ
    -0.08
    BY
    -0.08
    IDS
    -0.08
    说çĿĢ
    -0.08
    POSITIVE LOGITS
    èĨĺ
    0.09
    -nil
    0.09
    éĥ½æĹłæ³ķ
    0.09
    æĥħæĬ¥
    0.09
    ä¸Ģåı¥
    0.08
    磬
    0.08
    æĦıä¹īä¸Ĭ
    0.08
    æĪijåİ»
    0.08
    窮
    0.08
    ä¸Ģå¹´å¤ļ
    0.08
    Activations Density 0.057%

    No Known Activations