© 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. 34755
    Prev
    Next
    INDEX
    Explanations

    HTML document structure

    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
    èĶĵ
    -0.09
    çĻ½æĸij
    -0.09
    pers
    -0.08
    èĪ±
    -0.08
    é«ĺåİŁ
    -0.08
    strup
    -0.08
    æĤ£æľī
    -0.08
     Kod
    -0.08
    Blockly
    -0.08
     Jungle
    -0.08
    POSITIVE LOGITS
    æĭĽ
    0.11
    èģĮä¸ļæĬĢæľ¯
    0.11
    çĤ¼
    0.10
    åIJĮç±»
    0.09
    转åĮĸ
    0.09
    çĤ
    0.09
    è§īéĨĴ
    0.09
    代
    0.09
    羿
    0.09
    çķĮ
    0.09
    Activations Density 0.072%

    No Known Activations