© 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. 16869
    Prev
    Next
    INDEX
    Explanations

    I think it

    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
     probably
    -0.13
    probably
    -0.11
     probable
    -0.11
     Probably
    -0.10
     likely
    -0.10
    thon
    -0.10
     basically
    -0.10
    oen
    -0.10
    ryan
    -0.09
     lik
    -0.09
    POSITIVE LOGITS
     they
    0.10
    orgot
    0.09
     thats
    0.09
    onna
    0.09
     should
    0.09
    asher
    0.09
    aben
    0.09
    unn
    0.09
     we
    0.09
     I
    0.09
    Activations Density 0.028%

    No Known Activations