© 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. 27050
    Prev
    Next
    INDEX
    Explanations

    all types/aspects/levels of

    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
    .jboss
    -0.09
    _vs
    -0.09
     Lev
    -0.09
    æ¯ı个人çļĦ
    -0.08
    å¾Īéĩįè¦ģçļĦ
    -0.08
    NCY
    -0.08
    ç¾¼
    -0.08
    æ¢Ĺ
    -0.08
    ä¸Ģ带
    -0.08
    æĽ´å¤ļ
    -0.08
    POSITIVE LOGITS
    _except
    0.11
     except
    0.10
    except
    0.09
    Except
    0.09
    åł°
    0.09
    大大å°ıå°ı
    0.09
    å°¤åħ¶æĺ¯
    0.09
     Except
    0.09
    ä¸ĵæłı
    0.09
    sep
    0.08
    Activations Density 0.042%

    No Known Activations