© 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. 49689
    Prev
    Next
    INDEX
    Explanations

    can't focus or sleep

    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
    udo
    -0.10
     już
    -0.08
    aper
    -0.08
     unemployed
    -0.08
    /container
    -0.08
     bog
    -0.08
     orders
    -0.08
    athed
    -0.08
     bluff
    -0.08
    zi
    -0.08
    POSITIVE LOGITS
     knowing
    0.14
     surrounded
    0.13
     Knowing
    0.12
     amid
    0.12
     worrying
    0.12
     nid
    0.11
     amidst
    0.11
     wondering
    0.10
    idis
    0.10
     fearing
    0.10
    Activations Density 0.018%

    No Known Activations