© 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. 61205
    Prev
    Next
    INDEX
    Explanations

    approached / approach

    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
    åıĪä¸Ģ次
    -0.11
    èķĥ
    -0.11
    elu
    -0.11
    æ³¥
    -0.10
     ÙĦدÙĬ
    -0.10
    .Must
    -0.10
    INCT
    -0.09
    æĢĿç´¢
    -0.09
    inks
    -0.09
    ç¾İ丽
    -0.09
    POSITIVE LOGITS
    èµ°è¿ij
    0.14
    ä¸Ĭåīį
    0.12
     approaches
    0.11
     Appro
    0.10
    éĿłè¿ij
    0.10
    è¿ĩæĿ¥
    0.10
    appro
    0.10
     front
    0.10
     Approach
    0.10
    éĢ¼è¿ij
    0.09
    Activations Density 0.028%

    No Known Activations