© 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. 32273
    Prev
    Next
    INDEX
    Explanations

    not enabled or not yet

    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
     alo
    -0.08
    å¼Ģæĭĵ
    -0.08
    rut
    -0.08
    pill
    -0.08
    èĢĮä¸į
    -0.08
    ÑİÑĢ
    -0.08
    ruc
    -0.08
    äºĨ解ä¸Ģä¸ĭ
    -0.08
    ies
    -0.07
     Scot
    -0.07
    POSITIVE LOGITS
    æŃ¤æ¬¡æ´»åĬ¨
    0.10
    å¯ĵ
    0.09
    éĢĢ
    0.09
    éŃģ
    0.08
     долж
    0.08
    æı¡æīĭ
    0.08
    æŃ£ä¹ī
    0.08
    aub
    0.08
    åįģéĩĮ
    0.08
     Spi
    0.08
    Activations Density 0.026%

    No Known Activations