© 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. 34188
    Prev
    Next
    INDEX
    Explanations

    Carmen, Maura, Phillips

    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
    åĩłå®¶
    -0.10
     watt
    -0.09
    å°¼äºļ
    -0.09
    ãģĹãģ¾ãģĹãĤĩãģĨ
    -0.08
    åİŁåŀĭ
    -0.08
    ÑĪибка
    -0.08
     Pré
    -0.08
    iare
    -0.08
     Swim
    -0.08
    伤亡
    -0.08
    POSITIVE LOGITS
    åģļé¥Ń
    0.09
    åĢŁåı£
    0.09
    unken
    0.09
     Louise
    0.09
    èĮ§
    0.08
    ugu
    0.08
    æ±ĩæĬ¥
    0.08
    icc
    0.08
    ilton
    0.08
    ennie
    0.08
    Activations Density 0.015%

    No Known Activations