© 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. 60866
    Prev
    Next
    INDEX
    Explanations

    names ending in mann or berger

    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
    sey
    -0.09
    Ĭ
    -0.09
    ouce
    -0.09
    æĹ¥æ¸IJ
    -0.09
    èĬĿ麻
    -0.09
    æĶ¾å®½
    -0.09
    èĨº
    -0.08
    gay
    -0.08
    hill
    -0.08
    aji
    -0.08
    POSITIVE LOGITS
    berger
    0.11
    èĻ¹æ¡¥
    0.10
    bies
    0.10
    elter
    0.10
    mann
    0.09
    endor
    0.09
    ungs
    0.09
     mann
    0.09
    auer
    0.09
    platz
    0.09
    Activations Density 0.372%

    No Known Activations