© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7605
    Prev
    Next
    INDEX
    Explanations

    more information

    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
    æĽ´å¤ļä¿¡æģ¯
    -0.13
    ÑĤ
    -0.11
    ry
    -0.10
     somewhat
    -0.10
    sp
    -0.09
    ãĤĤãģĨ
    -0.09
    å¤ļ彩
    -0.09
    ãģĦãģŁãĤī
    -0.09
    ãģĦãģ¾ãģĻ
    -0.09
    ê¹IJ
    -0.09
    POSITIVE LOGITS
    -than
    0.16
    _than
    0.14
     importantly
    0.13
     than
    0.13
    æł·çļĦ
    0.13
    _THAN
    0.13
    æŶåĢĻ
    0.12
    ThanOr
    0.12
    å¤ļåľ°
    0.12
    OrFail
    0.12
    Activations Density 0.219%

    No Known Activations