© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9698
    Prev
    Next
    INDEX
    Explanations

    security issues and policy

    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
    éĤł
    -0.09
    æįŁèĢĹ
    -0.09
    igua
    -0.09
    alsy
    -0.09
    该项
    -0.09
    ç»Ļä½łä»¬
    -0.09
    _except
    -0.09
    vos
    -0.09
    åıªè¦ģæľī
    -0.09
    dale
    -0.08
    POSITIVE LOGITS
    æݪæĸ½
    0.11
    æĦıè¯Ĩ
    0.11
    conscious
    0.09
     conscious
    0.09
    /security
    0.09
    大å±Ģ
    0.09
    Ñİ
    0.09
    ä¸įåĪ°ä½į
    0.09
    .Cryptography
    0.08
    -conscious
    0.08
    Activations Density 0.112%

    No Known Activations