© 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. 49718
    Prev
    Next
    INDEX
    Explanations

    NFL team names

    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
    äºī
    -0.10
    çķĻè¨Ģ
    -0.09
    æ·Į
    -0.09
    æµ·æ£ł
    -0.09
    äºĨä¸Ģä¼ļåĦ¿
    -0.09
    è¿ĻåĦ¿
    -0.08
    fos
    -0.08
    泫
    -0.08
    çľĭä¸įæĩĤ
    -0.08
    æ»ļæ»ļ
    -0.08
    POSITIVE LOGITS
    .bz
    0.10
    mann
    0.09
    æ®·
    0.09
    mel
    0.08
    acked
    0.08
    _INFINITY
    0.08
    è¿ĻæĶ¯
    0.08
    istan
    0.08
    箾
    0.08
    ðŁ¦Ħ
    0.08
    Activations Density 0.017%

    No Known Activations