© 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. 20208
    Prev
    Next
    INDEX
    Explanations

    election nominations and candidates

    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
    å«Ĥ
    -0.10
    æĸ°å¼Ģ
    -0.09
    å°ıåŀĭ
    -0.09
    课é¢ĺ
    -0.08
    å§Ĭ
    -0.08
    ipl
    -0.08
    ä¸Ģ对
    -0.08
    æĪŁ
    -0.08
    iki
    -0.08
    åįĹè·¯
    -0.08
    POSITIVE LOGITS
    åĢĻéĢī人
    0.14
    人éĢī
    0.14
    åĢĻéĢī
    0.14
    å½ĵéĢī
    0.13
    æıIJåIJį
    0.11
     candidate
    0.11
     candidates
    0.11
    èµĦ
    0.11
     Ware
    0.10
    æŃ¤äºº
    0.10
    Activations Density 0.070%

    No Known Activations