© 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. 54897
    Prev
    Next
    INDEX
    Explanations

    cause of

    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
    ora
    -0.10
    iple
    -0.08
    äºĨå¤ļå°ij
    -0.08
    ners
    -0.08
    é¢Ħ订
    -0.08
    åĸĦæĦı
    -0.08
    èĭĩ
    -0.08
    æĭŃ
    -0.08
     Luc
    -0.08
    伺
    -0.08
    POSITIVE LOGITS
    orthy
    0.11
    æĭĨ
    0.09
     Winn
    0.09
     Lug
    0.09
    utch
    0.09
    @brief
    0.09
     дело
    0.09
    äºĭä¸ļåıijå±ķ
    0.09
    è¯Ŀé¢ĺ
    0.09
    zar
    0.09
    Activations Density 0.027%

    No Known Activations