© 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. 57526
    Prev
    Next
    INDEX
    Explanations

    video games titles

    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
    è·ĥ
    -0.09
    èºį
    -0.09
    éĺ¶æ®µæĢ§
    -0.09
    ACS
    -0.08
    erra
    -0.08
    çŃĿ
    -0.08
    paced
    -0.08
     гÑĢ
    -0.08
    åįĥåı¤
    -0.08
    CAF
    -0.08
    POSITIVE LOGITS
    ç²Ĺç³Ļ
    0.10
    æ§İ
    0.10
    ç½ļ
    0.10
    çªĴ
    0.09
    ä¸įæĪIJ
    0.09
    gles
    0.09
     safeg
    0.09
    宽æĿ¾
    0.09
    egl
    0.09
    æģĤ
    0.09
    Activations Density 0.027%

    No Known Activations