© 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. 33919
    Prev
    Next
    INDEX
    Explanations

    right time or job

    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
    ilig
    -0.08
    åIJĮæł·æĺ¯
    -0.08
    ç®Ķ
    -0.08
    åºĩ
    -0.08
    èµ°å»Ĭ
    -0.08
    ots
    -0.08
    bai
    -0.07
    çĸ³
    -0.07
    åIJ¬åĬĽ
    -0.07
    é£ŀæī¬
    -0.07
    POSITIVE LOGITS
    éĢĤéĩı
    0.11
     timely
    0.10
    ä»·éĴ±
    0.10
    çĶ·åıĭ
    0.10
    å¡ŀ
    0.10
    ç¡Į
    0.09
    ç¨įç¨į
    0.09
    .ov
    0.09
    çĪ±ä¸Ĭ
    0.09
    æŶèĬĤ
    0.09
    Activations Density 0.061%

    No Known Activations