© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 28235
    Prev
    Next
    INDEX
    Explanations

    code snippets and variables

    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
    ï¼īãĢģ
    -0.22
    ãĢģ
    -0.11
    ãĢįãĢĮ
    -0.10
    <tr
    -0.10
    peg
    -0.09
     MMM
    -0.08
    ":"","
    -0.08
    =?,
    -0.08
     wah
    -0.08
    <th
    -0.08
    POSITIVE LOGITS
     [â̦]↵↵
    0.12
      ↵↵
    0.12
     .↵↵
    0.12
    *)↵↵
    0.12
    ++↵↵
    0.11
    "/></
    0.11
     [...]↵↵
    0.11
    #endregion
    0.11
    ↵↵
    0.10
     ↵↵
    0.10
    Activations Density 0.001%

    No Known Activations