© 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. 38871
    Prev
    Next
    INDEX
    Explanations

    of the most

    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
    ä¹°ä¸ľè¥¿
    -0.09
    tré
    -0.08
    äºİæѤ
    -0.08
    åľ¨è¿Ļ
    -0.08
    MR
    -0.08
    太太
    -0.08
    sert
    -0.08
    conc
    -0.08
    å°±è¿ij
    -0.08
    æľĢæĹ©
    -0.08
    POSITIVE LOGITS
    çļĦä¸ĢéĿ¢
    0.10
    æĻļå¹´
    0.10
    åĩłå¹´
    0.10
    brush
    0.09
    çĶ¥
    0.09
     Gala
    0.09
    eger
    0.09
    è¿Ļä¸Ģå¹´
    0.09
    ordes
    0.09
    .year
    0.09
    Activations Density 0.028%

    No Known Activations