© 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. 36388
    Prev
    Next
    INDEX
    Explanations

    life experiences, passions, and struggles

    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
    涣
    -0.10
    ä¸ĭåįĬ
    -0.10
     utrecht
    -0.09
    ä¸į让
    -0.09
    akov
    -0.09
    assis
    -0.09
    ä¸įåĩĨ
    -0.09
     thuyết
    -0.08
    æīĢ以说
    -0.08
    å¤ļå¤ļ
    -0.08
    POSITIVE LOGITS
    åĸľ
    0.10
     ups
    0.10
    æŃī
    0.09
     quir
    0.09
    èĩ§
    0.09
    æĢĿèĢĥ
    0.09
    _IOCTL
    0.09
    åĸľå¥½
    0.08
    /vendor
    0.08
    æ¯ı天éĥ½
    0.08
    Activations Density 0.074%

    No Known Activations