© 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. 55535
    Prev
    Next
    INDEX
    Explanations

    whitelist and blacklist

    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
    æ´»çĿĢ
    -0.09
    ç½²
    -0.09
    æ¤ģ
    -0.09
    .createComponent
    -0.09
    attle
    -0.09
    豫
    -0.09
    æ³ķå¾ĭ责任
    -0.09
    ẽ
    -0.08
    åħ¬åħ±æĸĩåĮĸ
    -0.08
    è±¹
    -0.08
    POSITIVE LOGITS
    åIJįåįķ
    0.14
    é»ijåIJįåįķ
    0.12
    list
    0.10
    æ´ĭ
    0.10
     blacklist
    0.09
    ListItem
    0.09
    åIJįå½ķ
    0.09
    -list
    0.09
    è±ģ
    0.09
     certain
    0.09
    Activations Density 0.113%

    No Known Activations