© 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. 2613
    Prev
    Next
    INDEX
    Explanations

    ion transport or mobility

    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
    ç¬ij
    -0.10
     dạng
    -0.10
    ween
    -0.10
    稿
    -0.09
    OOK
    -0.09
    ayas
    -0.09
    моÑĢ
    -0.09
    venge
    -0.09
    æĿĨèıĮ
    -0.09
    rian
    -0.09
    POSITIVE LOGITS
    иÑĤелей
    0.09
    æ®ĸ
    0.09
    åĮĸè¿Ľç¨ĭ
    0.09
     Abel
    0.09
    ization
    0.09
    çĸ¼
    0.08
    ographic
    0.08
    izable
    0.08
    isible
    0.08
    è¿Ļç¯ĩæĸĩç«ł
    0.08
    Activations Density 0.097%

    No Known Activations