© 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. 55205
    Prev
    Next
    INDEX
    Explanations

    :

    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
    èģĶ
    -0.10
    å¿ı
    -0.09
    ä¾Ľ
    -0.09
    ä¸ĢçĤ¹çĤ¹
    -0.09
    éĤ£æŶ
    -0.09
    èģ¯
    -0.08
    çĤ¹ç¼Ģ
    -0.08
    æĪijèĩªå·±
    -0.08
    _placement
    -0.08
    åı¦å¤ĸ
    -0.08
    POSITIVE LOGITS
    åľ¨ä¸Ģ个
    0.10
    .hs
    0.10
    é¦ĸè¦ģ
    0.10
    建åĨĽ
    0.09
    åIJ¬çĿĢ
    0.09
    åľ¨ä¸Ģ
    0.09
    ä¹į
    0.09
    helm
    0.09
    .hu
    0.09
    ep
    0.09
    Activations Density 0.028%

    No Known Activations