© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 24335
    Prev
    Next
    INDEX
    Explanations

    Midwest, western, Midlands

    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
    Negative Logits
    åįĹå±±
    -0.10
    jee
    -0.10
     Ñģобой
    -0.10
    gue
    -0.10
    esthesia
    -0.09
    个人è§ĤçĤ¹
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    é¦ĸéĥ½
    -0.08
    åĮĹ京åĨ¬å¥¥
    -0.08
    æµ·åı£
    -0.08
    POSITIVE LOGITS
    enty
    0.09
    -most
    0.09
    ward
    0.09
    ·
    0.09
     Minnesota
    0.09
    -serving
    0.09
    人士
    0.09
    åľ°åĮº
    0.08
    uron
    0.08
    igo
    0.08
    Activations Density 0.004%

    No Known Activations