© 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. 34037
    Prev
    Next
    INDEX
    Explanations

    authors and dates

    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
    ç¿İ
    -0.09
     tslint
    -0.08
    (ext
    -0.07
     Äijiá»ĥn
    -0.07
    å¤ļ彩
    -0.07
     Codes
    -0.07
    esco
    -0.07
    tement
    -0.07
    ill
    -0.07
    ðŁı»
    -0.07
    POSITIVE LOGITS
    ulate
    0.10
    çĮĽçĥĪ
    0.09
    plemented
    0.09
    igrate
    0.09
    è¿Ļ家
    0.09
    echa
    0.09
     ydk
    0.08
    cem
    0.08
    åŁİå¸Ĥ建设
    0.08
    ä¸įçŁ¥ä¸įè§ī
    0.08
    Activations Density 0.023%

    No Known Activations