© 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. 48715
    Prev
    Next
    INDEX
    Explanations

    armed groups or forces

    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
    sic
    -0.10
    ampler
    -0.09
    stroy
    -0.09
    éĦ¢
    -0.09
    iling
    -0.09
    dap
    -0.08
    ipsoid
    -0.08
    dam
    -0.08
    uyen
    -0.08
     Lansing
    -0.08
    POSITIVE LOGITS
    еÑģÑĤво
    0.10
    ÙĬØŃ
    0.09
    转载请
    0.09
    Ø·ÙĬ
    0.09
    éĹ¾
    0.09
    .dictionary
    0.09
    åĮ£
    0.09
    éĵĽ
    0.09
    è¿Ļæł·çļĦè¯Ŀ
    0.09
    æĢ»åħ¬åı¸
    0.09
    Activations Density 0.011%

    No Known Activations