© 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. 7623
    Prev
    Next
    INDEX
    Explanations

    borderline, boundary, intermediate, or fringe

    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
    è¾ľ
    -0.10
    lund
    -0.09
    éħįæĸĻ
    -0.09
    æĪ¿è½¦
    -0.08
    èĤ²åĦ¿
    -0.08
     tj
    -0.08
    çľ¨çľ¼
    -0.08
    çªģå¦Ĥ
    -0.08
    ä¸Ģ对
    -0.08
    åı£ç½©
    -0.08
    POSITIVE LOGITS
    åľ°å¸¦
    0.14
     borderline
    0.14
    è¾¹ç¼ĺ
    0.14
    è¾¹çķĮ
    0.13
    ä»ĭ
    0.12
    border
    0.12
    模ç³Ĭ
    0.12
     Border
    0.12
     border
    0.12
    çķĮéĻIJ
    0.12
    Activations Density 0.116%

    No Known Activations