© 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. 53846
    Prev
    Next
    INDEX
    Explanations

    what happened

    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
    onas
    -0.10
    大人
    -0.09
    èĢģ头
    -0.09
     ëĶ°
    -0.09
    ahas
    -0.08
    åĩłåĪĨ
    -0.08
    _pad
    -0.08
    寡
    -0.08
    onen
    -0.08
    éķ¿éķ¿
    -0.08
    POSITIVE LOGITS
    æģĭ
    0.10
    ertz
    0.09
    身边
    0.09
    éŀŃ
    0.09
    ä¼łè¯´
    0.09
    åĽ´ç»ķ
    0.09
    ichert
    0.09
    ìłĢ
    0.09
    æ²Ľ
    0.08
    éĢIJ
    0.08
    Activations Density 0.017%

    No Known Activations