© 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. 61457
    Prev
    Next
    INDEX
    Explanations

    difference between things

    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
    åIJĦæĸ¹éĿ¢
    -0.10
    eral
    -0.10
    ãģ¤ãģĦ
    -0.10
    .escape
    -0.09
    åģ¶
    -0.09
    æľĢå¿«
    -0.09
     tầm
    -0.09
    åĽŀæĬ¥
    -0.08
     Hindus
    -0.08
    minor
    -0.08
    POSITIVE LOGITS
     shortfall
    0.12
    弥补
    0.11
    äºĮèĢħ
    0.11
    å·®
    0.11
    è¡¥åħħ
    0.10
    å·®è·Ŀ
    0.10
     difference
    0.10
    å·®å¼Ĥ
    0.10
    缺åı£
    0.10
    å·®åĪ«
    0.10
    Activations Density 0.183%

    No Known Activations