© 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. 38269
    Prev
    Next
    INDEX
    Explanations

    Saturday Night Live

    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
    寡
    -0.10
    ç½ijç»ľä¼łæĴŃ
    -0.09
    å¼¼
    -0.09
    æ·¡æ·¡çļĦ
    -0.09
    åįĹ京å¸Ĥ
    -0.09
    _TAC
    -0.08
    ä¸Ī
    -0.08
    åľ°æ®µ
    -0.08
    marvin
    -0.08
    hti
    -0.08
    POSITIVE LOGITS
    Ñģоб
    0.10
    bst
    0.09
    chal
    0.08
    注æĺİ
    0.08
    å
    0.08
    تÙĥ
    0.08
    å¥ĩ迹
    0.08
    空ä¸Ń
    0.08
    è¤
    0.08
    å¿ħä¸įåı¯
    0.08
    Activations Density 0.006%

    No Known Activations