© 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. 25404
    Prev
    Next
    INDEX
    Explanations

    value in struct

    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
     eman
    -0.06
    oom
    -0.06
    <|fim_middle|>
    -0.06
     poss
    -0.06
     ad
    -0.06
    &
    -0.06
     contemporary
    -0.06
     ti
    -0.06
     &
    -0.06
    onna
    -0.06
    POSITIVE LOGITS
    IFn
    0.15
    /Dk
    0.14
    groupon
    0.14
    /repos
    0.13
    aji
    0.13
    :\/\/
    0.13
    Evt
    0.12
     Caval
    0.12
    Jvm
    0.12
    /dc
    0.12
    Activations Density 0.009%

    No Known Activations