© 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. 19642
    Prev
    Next
    INDEX
    Explanations

    secure / securing / secured

    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
    容å¿į
    -0.10
    éĶħ
    -0.09
    ç±į
    -0.09
    èķĥ
    -0.09
    (dw
    -0.08
    ä¸įåı¯
    -0.08
     tolerance
    -0.08
     Sever
    -0.08
    udi
    -0.08
    ston
    -0.08
    POSITIVE LOGITS
    è´§æºIJ
    0.11
    Kr
    0.10
    éĶĢåĶ®æ¸łéģĵ
    0.10
    çļĦåĪ©çĽĬ
    0.09
    secure
    0.09
     Passage
    0.09
     passage
    0.09
    ification
    0.09
    ä½ıäºĨ
    0.09
    afia
    0.09
    Activations Density 0.068%

    No Known Activations