© 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. 19211
    Prev
    Next
    INDEX
    Explanations

    disclaimer or caveat

    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
    Anth
    -0.10
    OnInit
    -0.10
    .ua
    -0.09
    磺
    -0.09
    贵宾
    -0.09
    .indices
    -0.09
    å
    -0.08
    æ§Ĭ
    -0.08
    å¨ģèĥģ
    -0.08
    æĺĤ
    -0.08
    POSITIVE LOGITS
     disclaimer
    0.13
     caveat
    0.12
    éĻIJå®ļ
    0.11
    Disclaimer
    0.11
     cave
    0.10
     Disclaimer
    0.10
    è°¨æħİ
    0.10
     пÑĢин
    0.10
    å¤ĩ注
    0.10
    å¿ħä¸įåı¯å°ij
    0.09
    Activations Density 0.074%

    No Known Activations