© 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. 48143
    Prev
    Next
    INDEX
    Explanations

    role or category label

    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
     Sext
    -0.09
    Æ¡
    -0.09
     drafts
    -0.09
    åĥıæĺ¯
    -0.09
    ÌĢ
    -0.09
    缪
    -0.09
    _leave
    -0.08
    ncy
    -0.08
     THEORY
    -0.08
    ç®Ĺæĺ¯
    -0.08
    POSITIVE LOGITS
    ä¹ĭä¸Ģ
    0.14
     gì
    0.10
    绯
    0.09
    æ¶İ
    0.09
    åħ¬å¼Ģåıij
    0.09
    æĬ½
    0.09
    ä¸Ľä¹¦
    0.09
    溯æºIJ
    0.09
    .Tensor
    0.08
    èĸ°
    0.08
    Activations Density 0.225%

    No Known Activations