© 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. 5096
    Prev
    Next
    INDEX
    Explanations

    if so

    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
    -0.08
     Match
    -0.08
    Jam
    -0.07
    åĴĮ个人
    -0.07
    åĮ¹éħį
    -0.07
    溶解
    -0.07
    æ¢Ĺ
    -0.07
    æī§æ³ķ
    -0.07
    mons
    -0.07
    qu
    -0.07
    POSITIVE LOGITS
    å¦Ĥæŀľæĺ¯
    0.13
    ä¸ĩä¸Ģ
    0.11
    å¦Ĥæŀľä¸įæĺ¯
    0.11
    áŀķ
    0.10
    åIJİèĢħ
    0.10
    jp
    0.10
    å¦Ĥæŀľæľī
    0.10
    å¾Ļ
    0.10
    ypress
    0.09
    éĢµ
    0.09
    Activations Density 0.071%

    No Known Activations