© 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. 6050
    Prev
    Next
    INDEX
    Explanations

    attack / attacks

    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
     rÃłng
    -0.11
    è¾Ī
    -0.10
    irty
    -0.10
    ãģĦãģĨ
    -0.10
     dÃłng
    -0.10
    ocket
    -0.09
    æĽ·
    -0.09
    çIJ°
    -0.09
    ĺ
    -0.09
    hift
    -0.09
    POSITIVE LOGITS
    able
    0.12
    iveness
    0.10
    èĢħ
    0.09
    itel
    0.09
     aVar
    0.09
    Occurred
    0.09
    sha
    0.08
    èĢħçļĦ
    0.08
    acked
    0.08
    ABLE
    0.08
    Activations Density 0.023%

    No Known Activations