© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5957
    Prev
    Next
    INDEX
    Explanations

    if you will

    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
    _INLINE
    -0.13
    éĽī
    -0.09
    ä¸įä¼ļ
    -0.09
    ç¥ļ
    -0.09
    çªľ
    -0.09
    ERING
    -0.09
    ä¸įçĶĺ
    -0.09
    aku
    -0.09
    PIP
    -0.09
    èµŀèµı
    -0.09
    POSITIVE LOGITS
    Ñħа
    0.09
    åIJĪæł¼
    0.08
    åĨľä¸ļç§ijæĬĢ
    0.08
    ÑĪка
    0.08
    iture
    0.08
    idget
    0.08
    _Dep
    0.08
    oise
    0.08
    enta
    0.08
     Martins
    0.08
    Activations Density 0.003%

    No Known Activations