© 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. 17421
    Prev
    Next
    INDEX
    Explanations

    resource availability and opportunity

    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
    æĶ¯æŁ±
    -0.09
    æī§æĦı
    -0.09
    ä¸įçķĻ
    -0.09
    ä¸įåĩĨ
    -0.09
    rys
    -0.08
     Leh
    -0.08
    ä¸įè´Ł
    -0.08
    _extra
    -0.08
    entropy
    -0.08
    æľĢåĪĿ
    -0.08
    POSITIVE LOGITS
    æ½ľåĬĽ
    0.18
    æ½ľåľ¨
    0.14
    æ½ľèĥ½
    0.13
     potential
    0.12
     Potential
    0.12
    æľīèĥ½åĬĽ
    0.12
    èµĦæºIJä¼ĺåĬ¿
    0.12
    åħ·å¤ĩ
    0.11
    å®Įåħ¨åı¯ä»¥
    0.11
    èķ´
    0.11
    Activations Density 0.192%

    No Known Activations