© 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. 61052
    Prev
    Next
    INDEX
    Explanations

    lost film preservation

    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
    Raised
    -0.10
     raised
    -0.09
    ç§ijæĬĢè¿ĽæŃ¥
    -0.09
    è¿ģ
    -0.09
    åij¨åĽ´çļĦ
    -0.08
    æĬĬèĩªå·±çļĦ
    -0.08
    dn
    -0.08
     spill
    -0.08
    _pick
    -0.08
    è¿ĻäºĽäºº
    -0.08
    POSITIVE LOGITS
    å®Įæķ´
    0.14
    æ®ĭ
    0.13
    ä¿ĿåŃĺ
    0.13
     ÑģоÑħÑĢани
    0.12
    å®Įæķ´çļĦ
    0.11
    丢失
    0.11
    缺失
    0.11
    éģĹ
    0.11
     lost
    0.11
    ä½ļ
    0.11
    Activations Density 0.148%

    No Known Activations