© 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. 18036
    Prev
    Next
    INDEX
    Explanations

    permission to do something

    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
    åįĬ天
    -0.11
    ä¸Ńæĸ°
    -0.10
    宸
    -0.09
    åı¦æľī
    -0.09
    ç¨Ķ
    -0.09
    鸵
    -0.08
    嵯
    -0.08
    Esc
    -0.08
    æĸ°éĹ»ç½ij
    -0.08
    åı¯æݧ
    -0.08
    POSITIVE LOGITS
    é©°
    0.11
    åıijæĮ¥
    0.11
    loo
    0.11
    å¾Ĺ以
    0.10
    åĮĸè¿Ľç¨ĭ
    0.09
    缴
    0.09
     freely
    0.09
    yster
    0.09
    æĮł
    0.09
    è·¨
    0.09
    Activations Density 0.230%

    No Known Activations