© 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. 49592
    Prev
    Next
    INDEX
    Explanations

    nuisance, impairments, manufacture, survey, care

    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
    åĺīå¹´åįİ
    -0.09
    è¹¼
    -0.09
    è°´
    -0.09
    urt
    -0.08
    çĽı
    -0.08
    è¡Įç¨ĭ
    -0.08
    ög
    -0.08
    åħħå®ŀ
    -0.08
     Lund
    -0.08
    ä¸ļæĢģ
    -0.08
    POSITIVE LOGITS
    ç®ķ
    0.09
    åĴĮå°ļ
    0.09
    _TERM
    0.09
     ÙĨÙĬÙĪز
    0.09
    鬼
    0.08
     ترÙĥ
    0.08
    -scalable
    0.08
    缪
    0.08
    éķĿ
    0.08
     CAST
    0.08
    Activations Density 1.481%

    No Known Activations