© 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. 15176
    Prev
    Next
    INDEX
    Explanations

    teach someone something

    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
    uli
    -0.14
    ulia
    -0.13
    ough
    -0.11
    atori
    -0.10
    olation
    -0.10
    Advice
    -0.10
    XT
    -0.10
    asco
    -0.10
    ulating
    -0.10
    ULE
    -0.10
    POSITIVE LOGITS
     us
    0.13
    /train
    0.11
     courses
    0.10
     him
    0.10
     taught
    0.10
     lessons
    0.09
    /show
    0.09
    ASI
    0.09
     them
    0.09
    ings
    0.08
    Activations Density 0.017%

    No Known Activations