© 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. 11629
    Prev
    Next
    INDEX
    Explanations

    academic positions and titles

    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
     iid
    -0.09
    ia
    -0.09
    à¸Ńà¸ļ
    -0.09
    ç¿»å¼Ģ
    -0.08
    dia
    -0.08
     Iss
    -0.08
    fec
    -0.08
    ivan
    -0.08
    éļ°
    -0.08
    ided
    -0.08
    POSITIVE LOGITS
    Ñħи
    0.09
    æķķ
    0.09
    éĢĥéģ¿
    0.09
    allery
    0.09
    èIJ¥åķĨ
    0.08
    .inverse
    0.08
    robe
    0.08
    .escape
    0.08
    vron
    0.08
    å¾ħ
    0.08
    Activations Density 0.082%

    No Known Activations