© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115505
    Prev
    Next
    INDEX
    Explanations

    practice and training sessions

    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
     liter
    -0.09
    Mom
    -0.08
     cin
    -0.08
    cia
    -0.08
    rog
    -0.08
     Deg
    -0.08
    ï¸
    -0.08
     Mom
    -0.08
    success
    -0.08
     washing
    -0.08
    POSITIVE LOGITS
     sessions
    0.19
     session
    0.14
     schedules
    0.14
     schedule
    0.13
    /play
    0.13
     Sessions
    0.13
    essions
    0.12
     Twice
    0.12
    /pr
    0.12
    /testing
    0.12
    Activations Density 0.089%

    No Known Activations