© 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. 29844
    Prev
    Next
    INDEX
    Explanations

    encoding and escaping characters

    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
    styles
    -0.11
    ibold
    -0.10
    aju
    -0.10
    tep
    -0.10
     noop
    -0.10
     dalla
    -0.10
    atism
    -0.10
     Bak
    -0.10
    award
    -0.10
    span
    -0.10
    POSITIVE LOGITS
     them
    0.15
     certain
    0.12
     everything
    0.10
     some
    0.10
     incoming
    0.10
    /animate
    0.09
    /sl
    0.09
    them
    0.09
     things
    0.09
    fy
    0.08
    Activations Density 0.799%

    No Known Activations