© 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. 48893
    Prev
    Next
    INDEX
    Explanations

    dialog box

    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
    æĮł
    -0.09
    çĦ¶æĺ¯
    -0.08
    itulo
    -0.08
    ders
    -0.08
    weis
    -0.08
    flix
    -0.08
    coat
    -0.08
    lius
    -0.08
    quis
    -0.08
    ³
    -0.08
    POSITIVE LOGITS
    ues
    0.14
    uality
    0.10
    çŨ
    0.10
    plorer
    0.10
    arrant
    0.10
    ysis
    0.10
    بة
    0.09
    ossal
    0.09
    UES
    0.09
    ymm
    0.09
    Activations Density 0.038%

    No Known Activations