© 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. 33782
    Prev
    Next
    INDEX
    Explanations

    competition registration events

    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
    TRACE
    -0.09
    onic
    -0.09
    å¾ģæ±Ĥ
    -0.08
    请大家
    -0.08
    lect
    -0.08
    å¤ļä¹ħ
    -0.08
    iman
    -0.08
    å«ĸ
    -0.08
     tenure
    -0.08
    åģıä½İ
    -0.08
    POSITIVE LOGITS
    åıĤèµĽ
    0.13
    ç«ŀèµĽ
    0.11
    æ¯ĶèµĽ
    0.11
    éĢīæĭĶ
    0.11
    é¢Ħå¤ĩ
    0.10
    åĨ³èµĽ
    0.10
    éĢīæīĭ
    0.10
    æ¯ĶèµĽä¸Ń
    0.10
    çļĦç«ŀäºī
    0.10
    å±ķæ¼Ķ
    0.10
    Activations Density 0.074%

    No Known Activations