© 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. 30296
    Prev
    Next
    INDEX
    Explanations

    number or punctuation

    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
    ""↵
    -0.13
    &gt
    -0.12
    (import
    -0.12
    &apos
    -0.12
    ,},↵
    -0.11
    .\"
    -0.11
    qli
    -0.11
    &nbsp
    -0.11
    /&
    -0.11
    "in
    -0.10
    POSITIVE LOGITS
     (
    0.68
    ï¼Ī
    0.41
     (!
    0.36
     ("
    0.35
     (=
    0.35
     ï¼Ī
    0.35
     (*
    0.34
     ('
    0.34
     (“
    0.33
     (?
    0.33
    Activations Density 8.905%

    No Known Activations