© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53003
    Prev
    Next
    INDEX
    Explanations

    agile iterations and development processes

    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
    _segment
    -0.10
    为å¥ijæľº
    -0.09
    åĩºè·¯
    -0.09
    äºĮ代
    -0.09
    æĮ½
    -0.09
    .uniform
    -0.09
    ç§ĥ
    -0.08
    æŃ¤é¡¹
    -0.08
    é¼ĵ
    -0.08
    课å¤ĸ
    -0.08
    POSITIVE LOGITS
    æµģç¨ĭ
    0.11
    è¿ĩç¨ĭ
    0.11
     process
    0.09
     cycle
    0.09
    steps
    0.09
    æĭĪ
    0.09
     adopt
    0.09
    è´¨éĩı管çIJĨ
    0.09
     steps
    0.09
    æŃ¥éª¤
    0.09
    Activations Density 0.166%

    No Known Activations