© 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. 18769
    Prev
    Next
    INDEX
    Explanations

    draft legislation, EPA, Indiana, law

    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
    ثر
    -0.08
    ovation
    -0.08
     ÑģамÑĭм
    -0.08
    ties
    -0.08
    ders
    -0.08
    INDER
    -0.08
    hue
    -0.08
    gere
    -0.08
    ows
    -0.08
    ollo
    -0.08
    POSITIVE LOGITS
    ural
    0.11
    åħ¬åı¸ç«łç¨ĭ
    0.11
    ught
    0.10
    ãģĤãĤĭ
    0.10
     hè
    0.10
    è¯Ĥ
    0.10
    ree
    0.10
    åĬ©éķ¿
    0.10
    edList
    0.09
    ings
    0.09
    Activations Density 0.018%

    No Known Activations