© 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. 57823
    Prev
    Next
    INDEX
    Explanations

    media publications or news agencies

    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
    åįĸç»Ļ
    -0.09
     \`
    -0.09
    çļĤ
    -0.08
    寰
    -0.08
    çıĤ
    -0.08
    DU
    -0.08
    ä½ľä¸ºä¸Ģ个
    -0.08
    راس
    -0.08
     Prä
    -0.08
    ENDOR
    -0.08
    POSITIVE LOGITS
    éĩĩ访æŶ
    0.11
    çķĻä¸ĭäºĨ
    0.09
    åģļè¿ĩ
    0.09
    _compat
    0.09
    ÑģоÑĤ
    0.09
    é«ĺçŃī
    0.09
    åĭĸ
    0.09
    åIJ¬ä¼Ĺ
    0.09
     Lind
    0.08
    æĹ¶è¡¨ç¤º
    0.08
    Activations Density 0.048%

    No Known Activations