© 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. 31157
    Prev
    Next
    INDEX
    Explanations

    three letters picked

    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
    两ç§į
    -0.10
    æIJª
    -0.09
    大家åĪĨ享
    -0.09
    nd
    -0.09
    оÑĢо
    -0.09
    ilities
    -0.09
    eenth
    -0.08
    ADIO
    -0.08
    irector
    -0.08
    è¿Ļ两ç§į
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸ī个
    0.21
    rd
    0.20
    -quarters
    0.17
    ä¸īä½į
    0.16
    ä¸ī家
    0.15
    ä¸ī大
    0.14
    ä¸ī人
    0.14
    ä¸ī个
    0.14
     Three
    0.14
    Three
    0.13
    Activations Density 0.649%

    No Known Activations