© 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. 59058
    Prev
    Next
    INDEX
    Explanations

    password and secrets

    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
    å¼Ĥ
    -0.09
    åĪģ
    -0.09
    è°ĥ
    -0.08
     Tobacco
    -0.08
    ingles
    -0.08
    鬥
    -0.08
     Abr
    -0.08
     Hook
    -0.08
    ulant
    -0.08
    çķ°
    -0.08
    POSITIVE LOGITS
    ä½ĵè´´
    0.09
    vault
    0.09
    _PASSWORD
    0.09
    æĹĭ
    0.09
     Vaults
    0.09
     vault
    0.09
    éľīç´ł
    0.09
    æĸŃ
    0.08
     pad
    0.08
    _password
    0.08
    Activations Density 0.121%

    No Known Activations