© 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. 17151
    Prev
    Next
    INDEX
    Explanations

    comparisons of properties and states

    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
    æĥħåĨµä¸ĭ
    -0.09
    Millis
    -0.09
    åĽłç´ł
    -0.09
    edm
    -0.09
    æī©å®¹
    -0.09
    fall
    -0.08
    æ¦Ĥ
    -0.08
    æĸ¹éĿ¢çļĦ
    -0.08
    igation
    -0.08
    .currentPage
    -0.08
    POSITIVE LOGITS
    è¿Ľè´§
    0.10
    è¿Ļ段
    0.09
    çİ°éĩijæµģ
    0.09
    起身
    0.08
    åIJįåŃĹ
    0.08
     margins
    0.08
    顶å±Ĥ设计
    0.08
    ç¬ij容
    0.08
     наÑĩ
    0.08
    åħ¶
    0.08
    Activations Density 0.491%

    No Known Activations