© 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. 35712
    Prev
    Next
    INDEX
    Explanations

    until now

    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
    éĥ§
    -0.09
    æĪĸåħ¶ä»ĸ
    -0.09
    èĤ¥
    -0.09
    like
    -0.08
    ä¼ļä¸Ĭ
    -0.08
    ä¸ĢéĹª
    -0.08
    èݳ
    -0.08
    enge
    -0.08
    å¼ij
    -0.08
     Engel
    -0.08
    POSITIVE LOGITS
    ä¸ĭåįĬ
    0.11
    oader
    0.10
    irmed
    0.09
    imps
    0.09
    rightness
    0.09
    èĨĬ
    0.09
    æľīä¸Ģ天
    0.09
    _raise
    0.09
    oned
    0.09
    ä¸ĭæīĭ
    0.09
    Activations Density 0.020%

    No Known Activations