© 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. 28458
    Prev
    Next
    INDEX
    Explanations

    idle or idol

    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
     bend
    -0.09
    ulative
    -0.09
     bends
    -0.09
     Aub
    -0.09
    apis
    -0.09
    uche
    -0.09
    rel
    -0.09
    ialis
    -0.09
    rij
    -0.09
    èĹı
    -0.08
    POSITIVE LOGITS
     chatter
    0.13
    /id
    0.12
     gossip
    0.12
    wild
    0.12
    WAYS
    0.11
     curiosity
    0.11
     idle
    0.11
     pursuits
    0.11
     conce
    0.10
    bk
    0.10
    Activations Density 0.013%

    No Known Activations