© 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. 9841
    Prev
    Next
    INDEX
    Explanations

    detail, detailed, details

    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
    sWith
    -0.09
    çĦ¶æĺ¯
    -0.09
    è¦ģçŁ¥éģĵ
    -0.09
    殿ä¸ĭ
    -0.09
    棣
    -0.08
     Saw
    -0.08
    åIJĦçķĮ
    -0.08
    eer
    -0.08
    å¤§éĽ¨
    -0.08
    ider
    -0.08
    POSITIVE LOGITS
    sects
    0.09
    -rich
    0.09
    微信åı·
    0.09
    èĻĴ
    0.09
    aryl
    0.09
    ë§ģ
    0.09
    主管
    0.09
     Girlfriend
    0.09
    éĶIJ
    0.09
    stroy
    0.08
    Activations Density 0.017%

    No Known Activations