© 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. 28024
    Prev
    Next
    INDEX
    Explanations

    office or department services

    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
    éĺĸ
    -0.10
    .ALIGN
    -0.09
    ä¸Ģ举
    -0.09
    Manip
    -0.09
    èĬĴ
    -0.09
    ServiceImpl
    -0.09
    odus
    -0.09
    æĵį纵
    -0.09
    该åħ¬åı¸
    -0.09
    ç¥ł
    -0.09
    POSITIVE LOGITS
    æĭĽ
    0.11
    ä½Ĩæĺ¯æĪij
    0.09
    åľ¨åŃ¦æł¡
    0.08
    å¤ĸåĮħ
    0.08
     dep
    0.08
    ç§ij
    0.08
    kit
    0.08
    мед
    0.08
    人åijĺ
    0.08
    éĩı
    0.08
    Activations Density 0.044%

    No Known Activations