© 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. 29742
    Prev
    Next
    INDEX
    Explanations

    tramping, trailer, trading, travis, actor

    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
    éľĸ
    -0.09
    DET
    -0.08
    REW
    -0.08
    é¼¾
    -0.08
    ondere
    -0.08
    æĬ¥
    -0.08
    æ§Ľ
    -0.08
    å¾Īå¼Ģå¿ĥ
    -0.08
    ening
    -0.08
    andard
    -0.08
    POSITIVE LOGITS
    ities
    0.11
    /tr
    0.10
    迹
    0.10
    (TR
    0.09
    ALSE
    0.09
     aff
    0.09
    иÑĤÑĮÑģÑı
    0.09
    éļľç¢į
    0.08
    iple
    0.08
    åľī
    0.08
    Activations Density 0.031%

    No Known Activations