© 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. 33249
    Prev
    Next
    INDEX
    Explanations

    should be

    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
    _RSP
    -0.09
    å²Ĥ
    -0.09
    ç«ŁçĦ¶
    -0.09
    çĻ½çĻ½
    -0.08
    å¾Ģå¾Ģæĺ¯
    -0.08
    çļĦé«ĺ度
    -0.08
    ayne
    -0.08
    ä¼¼ä¹İ
    -0.08
    ç«
    -0.08
    ä¸įå¦Ĥ
    -0.08
    POSITIVE LOGITS
    äºĨåIJ§
    0.10
    ered
    0.10
    ä¸įåºĶ该
    0.09
    yla
    0.09
    ä¸įä¼ļæľī
    0.09
    ä¸įä¼ļåĨį
    0.09
    å¹´åºķåīį
    0.09
    没éĹ®é¢ĺ
    0.09
    reed
    0.09
     soon
    0.09
    Activations Density 0.047%

    No Known Activations