© 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. 7471
    Prev
    Next
    INDEX
    Explanations

    difficult or easy to do/achieve

    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
     Claw
    -0.12
     retro
    -0.12
    ilon
    -0.12
    sei
    -0.11
     purposely
    -0.11
    _usr
    -0.11
    maal
    -0.11
     walkthrough
    -0.11
     continually
    -0.11
    ecessarily
    -0.10
    POSITIVE LOGITS
     handling
    0.10
     cope
    0.09
     handle
    0.09
     survival
    0.08
     coping
    0.08
     cop
    0.08
     ordinary
    0.08
    pps
    0.08
     Handling
    0.08
     Os
    0.08
    Activations Density 0.268%

    No Known Activations