© 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. 4212
    Prev
    Next
    INDEX
    Explanations

    archived article

    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
    é¡¿
    -0.09
    _repository
    -0.09
    SKU
    -0.08
    éłĵ
    -0.08
    documentation
    -0.08
    夯
    -0.08
    常çĶ¨çļĦ
    -0.08
    ippet
    -0.08
    Elite
    -0.08
    VP
    -0.08
    POSITIVE LOGITS
    æĽ´å¤ļ精彩
    0.11
    è´£ç¼ĸ
    0.10
    aseline
    0.10
    个åĪ«
    0.10
    个人è§ĤçĤ¹
    0.09
    yor
    0.09
    èµŀèµı
    0.09
    缮æłĩä»»åĬ¡
    0.08
    mes
    0.08
     editorial
    0.08
    Activations Density 0.045%

    No Known Activations