© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 29690
    Prev
    Next
    INDEX
    Explanations

    release, escape, leaking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
     Stall
    -0.11
    arf
    -0.09
    wyn
    -0.09
    Mounted
    -0.09
     stalls
    -0.09
     carrot
    -0.09
     stall
    -0.09
    ymm
    -0.09
     tracing
    -0.09
     blanks
    -0.09
    POSITIVE LOGITS
     released
    0.31
     escape
    0.30
     escaping
    0.29
     escapes
    0.28
     leaking
    0.28
     release
    0.28
     escaped
    0.28
     leakage
    0.28
     Released
    0.28
     leaked
    0.27
    Activations Density 0.204%

    No Known Activations