© 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. 21981
    Prev
    Next
    INDEX
    Explanations

    time intervals

    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
    襦
    -0.09
    tru
    -0.08
     backpage
    -0.08
    _DICT
    -0.08
    rego
    -0.08
    åij·
    -0.08
    MAND
    -0.08
    èĩ³ä»Ĭ
    -0.08
    åīį身
    -0.08
    à¸Īà¸Ļ
    -0.08
    POSITIVE LOGITS
    æŃ¤åŁºç¡Ģä¸Ĭ
    0.12
    马æĭī
    0.10
    人æĿĥ
    0.10
    éģĩä¸Ĭ
    0.10
    举
    0.09
    ä»Ĩ
    0.09
    еле
    0.09
    nel
    0.09
    å«Ķ
    0.09
    ä»įåľ¨
    0.09
    Activations Density 0.307%

    No Known Activations