© 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. 50523
    Prev
    Next
    INDEX
    Explanations

    ballet

    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
    less
    -0.10
    linger
    -0.10
    orial
    -0.10
    å¿¡
    -0.10
    楣
    -0.09
    GED
    -0.09
    ewire
    -0.09
    éĥĽ
    -0.09
    äºĨä¸Ģåı£æ°Ķ
    -0.09
    yme
    -0.09
    POSITIVE LOGITS
    istically
    0.10
    ä¸Ģåľº
    0.10
    istic
    0.10
    æ¤ħ
    0.09
     sĩ
    0.09
    ists
    0.09
    ج
    0.09
    æľ¨åľ°æĿ¿
    0.09
    hammer
    0.09
    ä½Ĩä¸įéĻIJ
    0.09
    Activations Density 0.002%

    No Known Activations