© 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. 6896
    Prev
    Next
    INDEX
    Explanations

    all rights reserved

    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
    iry
    -0.10
    oning
    -0.09
     Alley
    -0.09
    uka
    -0.08
    wich
    -0.08
     Gin
    -0.08
    otto
    -0.08
    ronic
    -0.08
    ivity
    -0.08
    gor
    -0.08
    POSITIVE LOGITS
     Karn
    0.10
    (fr
    0.10
     thirst
    0.09
     toler
    0.09
     cutting
    0.09
     organ
    0.09
     chevy
    0.09
    nth
    0.09
    ascript
    0.09
     Maver
    0.09
    Activations Density 0.006%

    No Known Activations