© 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. 10645
    Prev
    Next
    INDEX
    Explanations

    Nexus One, Xbox One, Ubuntu One

    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
    æ®ĥ
    -0.10
    iles
    -0.09
    aoke
    -0.09
    .ends
    -0.08
     Barker
    -0.08
    oris
    -0.08
    /th
    -0.08
    éģIJ
    -0.08
    orial
    -0.08
    .getB
    -0.08
    POSITIVE LOGITS
    è¿Ļç¯ĩæĸĩç«ł
    0.10
    ÑģÑĮ
    0.09
    chaft
    0.09
    èĭĴ
    0.09
    uppen
    0.09
    ãĤ·ãĥ§ãĥĥãĥĹ
    0.08
     Damen
    0.08
    ä¸Ģ个个
    0.08
    çİ
    0.08
    volution
    0.08
    Activations Density 0.055%

    No Known Activations