© 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. 35595
    Prev
    Next
    INDEX
    Explanations

    Fife, Faisal, records, isek

    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
    ÑĤек
    -0.09
    surf
    -0.08
    sb
    -0.08
    sts
    -0.08
    listed
    -0.08
    è¡®
    -0.08
    ieux
    -0.08
    ç®´
    -0.07
    ä¾ĭè¡Į
    -0.07
     concent
    -0.07
    POSITIVE LOGITS
    кÑĥÑģ
    0.10
    åѤ
    0.09
    触æij¸
    0.09
    ä¼łéĹ»
    0.09
    èĦIJ
    0.08
    ALSE
    0.08
    REAM
    0.08
    .currentTime
    0.08
    èĪįä¸įå¾Ĺ
    0.08
    ä¸ŃåĽ½æĶ¿åºľ
    0.08
    Activations Density 0.007%

    No Known Activations