© 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. 9842
    Prev
    Next
    INDEX
    Explanations

    solution or problem resolution

    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
    å´Ķ
    -0.10
    å¿ł
    -0.09
    ä¸į代表
    -0.09
    åħ¨å¹´
    -0.09
    å»Ĭ
    -0.09
    é«ĺæ½®
    -0.08
    seo
    -0.08
    ruz
    -0.08
    åı®
    -0.08
    诬
    -0.08
    POSITIVE LOGITS
    解åĨ³
    0.12
    解åĨ³éĹ®é¢ĺ
    0.10
    çļĦæł¹æľ¬
    0.10
    解決
    0.09
    ÑĢеÑĪ
    0.09
    ä»İæł¹æľ¬
    0.09
    ä¹İ
    0.09
    èĢĮä¸įæĺ¯
    0.09
    ä»İæł¹æľ¬ä¸Ĭ
    0.09
    çĺķ
    0.09
    Activations Density 0.068%

    No Known Activations