© 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. 30605
    Prev
    Next
    INDEX
    Explanations

    explain how/what

    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
    ино
    -0.11
    .borderColor
    -0.10
    ä¸Ģçľ¼
    -0.10
    ÑĮе
    -0.10
    表æĥħ
    -0.09
    edException
    -0.09
    æĥħ趣
    -0.09
     Manning
    -0.09
    浪
    -0.09
    สาร
    -0.09
    POSITIVE LOGITS
    æĻ°
    0.15
    ä¸įæ¸ħæ¥ļ
    0.11
    ation
    0.11
    æ¸ħæ¥ļ
    0.11
     why
    0.10
    ä¸įæ¸ħ
    0.10
    éĢı
    0.09
    ä¸įæĺİçĻ½
    0.09
    аÑĤоÑĢ
    0.08
    oring
    0.08
    Activations Density 0.036%

    No Known Activations