© 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. 113832
    Prev
    Next
    INDEX
    Explanations

    tibial tendons

    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
     helpers
    -0.11
    emie
    -0.11
    coles
    -0.10
     Vu
    -0.10
    ست
    -0.10
    edes
    -0.10
    hoff
    -0.10
     Kapoor
    -0.10
     Wes
    -0.10
    okit
    -0.10
    POSITIVE LOGITS
    eder
    0.09
    erial
    0.09
     qualifying
    0.08
    emax
    0.08
     counter
    0.08
     labyrinth
    0.08
     circus
    0.08
    eman
    0.08
    rena
    0.08
     kicker
    0.08
    Activations Density 0.010%

    No Known Activations