© 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. 1904
    Prev
    Next
    INDEX
    Explanations

    through or via

    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
    æĢĿãģĦ
    -0.11
    æģ£
    -0.10
    æµ·æ£ł
    -0.09
    æĿ¥çľĭçľĭåIJ§
    -0.09
    åľ¨åħ¨åĽ½
    -0.09
    å¯ħ
    -0.09
    åľ¨åĽ½åĨħ
    -0.09
    缼
    -0.09
    æĢĿ绪
    -0.09
    å®ĥåı¯ä»¥
    -0.09
    POSITIVE LOGITS
    éĢļè¿ĩ
    0.19
    éĢļéģİ
    0.16
     through
    0.16
     via
    0.15
    via
    0.14
    through
    0.13
     ÑĩеÑĢез
    0.13
    éĢļè¿ĩ对
    0.13
     mediante
    0.13
    éĿł
    0.13
    Activations Density 0.467%

    No Known Activations