© 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. 2467
    Prev
    Next
    INDEX
    Explanations

    NIH grants and research

    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»ĭ
    -0.08
    ãģģ
    -0.08
    bserv
    -0.08
    屿
    -0.08
    .bz
    -0.08
    åı·çłģ
    -0.08
    лаÑģ
    -0.08
    tru
    -0.08
    ç²²
    -0.08
    æĮģ
    -0.08
    POSITIVE LOGITS
    责令
    0.10
    ä¸Ĭ游
    0.10
    ixer
    0.09
    å·¥ä½ľç»Ħ
    0.09
    宦
    0.09
    _DOT
    0.09
     ÑģÑĭÑĢ
    0.08
    乡
    0.08
    糸
    0.08
    è®°å¿ĨåĬĽ
    0.08
    Activations Density 0.068%

    No Known Activations