© 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. 53226
    Prev
    Next
    INDEX
    Explanations

    driving violations

    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
    æĢ¿
    -0.10
    ä¸Ģä¼ļ
    -0.10
    å±ĬæŶ
    -0.09
     PROVIDED
    -0.09
    失è°ĥ
    -0.09
    abar
    -0.09
    ç²¾éĢī
    -0.08
    缴è¾ĸå¸Ĥ
    -0.08
    å®Įå¤ĩ
    -0.08
    éªĪ
    -0.08
    POSITIVE LOGITS
    çݰ象
    0.09
    åĨł
    0.09
    té
    0.08
    Posting
    0.08
    Brains
    0.08
    屡
    0.08
     Diary
    0.08
     terr
    0.08
     Posting
    0.08
    éĢłæĪIJ
    0.08
    Activations Density 0.012%

    No Known Activations