© 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. 56494
    Prev
    Next
    INDEX
    Explanations

    resigned or held position

    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
    ä¿ĺ
    -0.10
    çĶŁæ°Ķ
    -0.09
    紧紧
    -0.09
    åŃ£
    -0.09
    éĨĴ
    -0.08
    è´Ń
    -0.08
    коп
    -0.08
    ä¸Ģåı£
    -0.08
     вал
    -0.07
    ä¼į
    -0.07
    POSITIVE LOGITS
    å±¥èģĮ
    0.17
    ä»»æľŁ
    0.17
    èģĮä½į
    0.14
    ä»»èģĮ
    0.14
    å±¥
    0.14
    ç«ŀéĢī
    0.14
    æī§æĶ¿
    0.13
    è¿°èģĮ
    0.12
    éĢī举
    0.12
     resign
    0.12
    Activations Density 0.150%

    No Known Activations