© 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. 39525
    Prev
    Next
    INDEX
    Explanations

    education, educated

    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
     Synd
    -0.10
     synd
    -0.09
    æħ¢æĢ§
    -0.09
     Kr
    -0.09
    æĥ§
    -0.09
    èµ°è·¯
    -0.08
    ients
    -0.08
    imos
    -0.08
    plat
    -0.08
    è£Ĥ
    -0.08
    POSITIVE LOGITS
     education
    0.11
    education
    0.10
    æķĻèĤ²
    0.09
    è´¨éĩı
    0.09
    educated
    0.09
    preset
    0.09
    (coll
    0.09
     educated
    0.09
    è¶ģ
    0.09
     Ñĥг
    0.09
    Activations Density 0.042%

    No Known Activations