© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 116552
    Prev
    Next
    INDEX
    Explanations

    exit and out

    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
     isolated
    -0.10
     Soci
    -0.10
     mast
    -0.10
     entering
    -0.09
     arrived
    -0.09
    iew
    -0.09
     arrive
    -0.09
    iah
    -0.09
    Entering
    -0.09
     Wie
    -0.09
    POSITIVE LOGITS
     nearest
    0.13
     exit
    0.12
    nearest
    0.11
     daylight
    0.11
     quickest
    0.10
     unsus
    0.10
    acci
    0.10
     beck
    0.09
    Exit
    0.09
     exits
    0.09
    Activations Density 0.007%

    No Known Activations