© 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. 56481
    Prev
    Next
    INDEX
    Explanations

    country music artist

    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
    ä¸Ģ个éĹ®é¢ĺ
    -0.10
    æľ¬ç½ij
    -0.09
    æ³ķå¾ĭ顾éĹ®
    -0.09
    è¶Ĭ大
    -0.09
    åIJĦåľ°
    -0.09
    æ¼ī
    -0.09
    媲
    -0.09
    udios
    -0.09
    iado
    -0.08
    æĭ©
    -0.08
    POSITIVE LOGITS
    _SCL
    0.10
    æ´¼
    0.08
    椿
    0.08
    nal
    0.08
    à¸ķา
    0.08
    æĺ¼å¤ľ
    0.08
    uir
    0.08
    expert
    0.08
    .TryParse
    0.08
    ê¾¼
    0.08
    Activations Density 0.018%

    No Known Activations