© 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. 17719
    Prev
    Next
    INDEX
    Explanations

    Fly Over

    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
    изм
    -0.10
    çļĦ人çĶŁ
    -0.08
    .cover
    -0.08
    rious
    -0.08
    æ¨Ĺ
    -0.08
    anoi
    -0.08
    缨
    -0.08
    opers
    -0.08
    /from
    -0.08
    æĥľ
    -0.08
    POSITIVE LOGITS
    adays
    0.09
    ylon
    0.09
    maal
    0.09
    éļ¾æĢª
    0.09
    äºĨ好
    0.08
    how
    0.08
    illard
    0.08
    keletal
    0.08
    oard
    0.08
    way
    0.07
    Activations Density 0.469%

    No Known Activations