© 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. 34086
    Prev
    Next
    INDEX
    Explanations

    design trends and ideas

    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
     зÑĢениÑı
    -0.09
    åĵĩ
    -0.09
    deen
    -0.09
     Dios
    -0.09
    (crate
    -0.08
    uem
    -0.08
    plen
    -0.08
    ìĭľíĤ¤
    -0.08
    è§Į
    -0.08
    usal
    -0.08
    POSITIVE LOGITS
     Ital
    0.10
    丰满
    0.09
    ured
    0.08
    åĽ¾æ¡Ī
    0.08
     поÑĩ
    0.08
    veloper
    0.08
    athan
    0.08
    ered
    0.08
    pri
    0.08
    ator
    0.08
    Activations Density 0.060%

    No Known Activations