© 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. 58310
    Prev
    Next
    INDEX
    Explanations

    security screening and procedures

    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
    kits
    -0.11
    зав
    -0.09
    etro
    -0.09
    нÑı
    -0.09
    isia
    -0.09
    ÑĢай
    -0.09
    æ¦ľ
    -0.09
    ews
    -0.08
    ä¿Ŀç¨İ
    -0.08
    ä½İå»ī
    -0.08
    POSITIVE LOGITS
    é»ĺå¥ij
    0.09
    æī«é»ij
    0.09
    è¿¢
    0.08
     thrill
    0.08
    æ°ijä¼ģ
    0.08
     Romance
    0.08
    rido
    0.08
    yb
    0.08
    寰
    0.08
     Civ
    0.08
    Activations Density 0.012%

    No Known Activations