© 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. 89427
    Prev
    Next
    INDEX
    Explanations

    shy or modest behavior

    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
     quietly
    -0.10
     calming
    -0.10
    icher
    -0.10
    entar
    -0.10
     greed
    -0.10
    Bookmark
    -0.10
    -hover
    -0.10
     tranqu
    -0.09
     Norton
    -0.09
     steadily
    -0.09
    POSITIVE LOGITS
     about
    0.13
     concerning
    0.12
    _about
    0.11
     regarding
    0.11
     talking
    0.10
     away
    0.10
     asking
    0.10
     discussing
    0.10
    away
    0.10
    about
    0.10
    Activations Density 0.004%

    No Known Activations