© 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. 5267
    Prev
    Next
    INDEX
    Explanations

    eyeliner and mascara, Country Club

    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
    æīĭä¸ŃçļĦ
    -0.10
    bum
    -0.09
    æĻļæĬ¥
    -0.09
    åĹ
    -0.09
    nap
    -0.09
    媳å¦ĩ
    -0.08
    wide
    -0.08
    _decorator
    -0.08
    reed
    -0.08
    ÑģÑĤи
    -0.08
    POSITIVE LOGITS
     полÑĮз
    0.10
    å®ŀæķĪ
    0.10
    ç°Į
    0.09
    /kubernetes
    0.09
    osex
    0.09
    çĿ¿
    0.09
    磫
    0.09
    ç§įç±»
    0.09
    æķĪæŀľ
    0.08
    篦
    0.08
    Activations Density 0.007%

    No Known Activations