© 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. 27327
    Prev
    Next
    INDEX
    Explanations

    python code, Bay, ica, ives, Sign

    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
    ged
    -0.10
    ä¿¡æģ¯åıijå¸ĥ
    -0.08
    磼
    -0.08
    ä»İ严
    -0.08
    istik
    -0.08
     Achilles
    -0.08
    å¾ģ
    -0.08
    æĢģ
    -0.08
    å½·
    -0.08
    Arg
    -0.07
    POSITIVE LOGITS
    èŀºä¸Ŀ
    0.10
    elves
    0.10
    è¯Ħ为
    0.09
    ä¸Ģåı·
    0.09
    æ®·
    0.09
    logue
    0.09
     Loves
    0.09
    beam
    0.09
    ç¾ŀ
    0.09
    èĬľ
    0.09
    Activations Density 0.002%

    No Known Activations