© 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. 31242
    Prev
    Next
    INDEX
    Explanations

    quite a descriptive adjective

    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
    æľ¬éĩij
    -0.08
    åĽŀæĿ¥
    -0.08
    riz
    -0.08
    æĽ´å¤§
    -0.07
     hal
    -0.07
    æ³ī
    -0.07
     Repo
    -0.07
    5
    -0.07
    9
    -0.07
     bott
    -0.07
    POSITIVE LOGITS
    ä¼ĺè¶Ĭ
    0.10
    æİ¥è¿ij
    0.10
    æµĵåİļ
    0.10
    è´´è¿ij
    0.10
    ä¸įéĢĤåIJĪ
    0.10
    .IM
    0.09
    çħŀ
    0.09
    éĢ»
    0.09
    åłĥ
    0.09
    _GP
    0.09
    Activations Density 0.078%

    No Known Activations