© 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. 38367
    Prev
    Next
    INDEX
    Explanations

    too / so / different

    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
    кÑĢ
    -0.10
    ä¸įéĶĻ
    -0.09
    ä¸įåIJĮç¨ĭ度
    -0.09
    å¯IJ
    -0.09
    å¾Ĺ罪
    -0.09
    ä¸įå¦Ĥ
    -0.09
    çĩĶ
    -0.09
    大å±Ģ
    -0.09
    æĤłæĤł
    -0.09
    è·¯çģ¯
    -0.09
    POSITIVE LOGITS
    è¿ĩå¤ļ
    0.10
     too
    0.09
    åħ®
    0.09
    åĹŁ
    0.09
    太å¤ļ
    0.09
    too
    0.09
    ä¹Łä¸įè¦ģ
    0.09
    ãģ°ãģĭãĤĬ
    0.09
    人æ°Ķ
    0.09
     TOO
    0.08
    Activations Density 0.045%

    No Known Activations