© 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. 50498
    Prev
    Next
    INDEX
    Explanations

    " or "

    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
    ç¨Ģ缺
    -0.11
    ãģ¦ãģĦ
    -0.10
    imator
    -0.09
    çĤ¸
    -0.09
    ä¸ĬéĻIJ
    -0.09
    irut
    -0.09
    å¥ĩ迹
    -0.09
    åĵªæĢķæĺ¯
    -0.09
     escap
    -0.09
    çªģåĩ»
    -0.09
    POSITIVE LOGITS
    åıĪ称
    0.11
    æ¶İ
    0.09
    æĪĸèĢħæĺ¯
    0.08
    ourke
    0.08
    hc
    0.08
    avage
    0.08
    å¦Ĥæľī
    0.07
    æ²IJæµ´
    0.07
     versatile
    0.07
    idor
    0.07
    Activations Density 0.266%

    No Known Activations