© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7537
    Prev
    Next
    INDEX
    Explanations

    popularity worldwide

    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
    gles
    -0.09
    éĩįåŀĭ
    -0.09
    ол
    -0.08
    iniz
    -0.08
    åİ¢
    -0.08
     NDP
    -0.08
    ernet
    -0.08
    itre
    -0.08
    imin
    -0.08
    hack
    -0.08
    POSITIVE LOGITS
    ENTIAL
    0.10
    idad
    0.10
    ÃŃsimo
    0.10
    èµ·æĿ¥äºĨ
    0.10
    ter
    0.09
    faction
    0.09
    èµ·æĿ¥
    0.09
    ÃŃs
    0.09
    åĴĮæĶ¯æĮģ
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.09
    Activations Density 0.021%

    No Known Activations