© 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. 61396
    Prev
    Next
    INDEX
    Explanations

    character or elements

    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
    ä¼ĺè´¨çļĦ
    -0.09
    对ä¼ģä¸ļ
    -0.09
    _activate
    -0.08
     ACLU
    -0.08
    ä¼ĺå¼Ĥ
    -0.08
    mania
    -0.08
    å¤ľ
    -0.08
    æĻºåķĨ
    -0.08
    åĬ£
    -0.08
    ä¸Ģé¢Ĺ
    -0.08
    POSITIVE LOGITS
    æµĵåİļ
    0.17
    æ°Ķæģ¯
    0.16
    æµĵæµĵçļĦ
    0.14
    æĢ§è´¨
    0.14
    çļĦæ°Ķæģ¯
    0.12
    çĹķ迹
    0.12
    åįģ足
    0.12
    çļĦåij³éģĵ
    0.11
    stamp
    0.11
    å«Įçĸij
    0.11
    Activations Density 0.031%

    No Known Activations