© 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. 50039
    Prev
    Next
    INDEX
    Explanations

    Field of Invention

    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
    ess
    -0.11
    Ùī
    -0.10
    fäh
    -0.10
    Ñĩик
    -0.09
    oto
    -0.09
    dır
    -0.09
    ë£Į
    -0.09
    ´
    -0.09
    ption
    -0.09
    ëį°
    -0.08
    POSITIVE LOGITS
    amp
    0.11
    ÑĤÑģÑı
    0.11
    RESH
    0.11
    work
    0.10
    ondon
    0.10
    ocusing
    0.10
     зÑĢениÑı
    0.10
    ร
    0.10
    ¨
    0.10
    spath
    0.10
    Activations Density 0.114%

    No Known Activations