© 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. 116599
    Prev
    Next
    INDEX
    Explanations

    | separators

    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
    =plt
    -0.09
    *this
    -0.09
    ï¼Ĵï¼IJ
    -0.09
     ↵↵↵↵
    -0.09
    /↵↵↵↵
    -0.09
    /////////////////////////////////////////////////////////////////////////////↵
    -0.09
    '↵↵↵↵
    -0.09
    meeting
    -0.09
    ..'
    -0.09
    //@
    -0.08
    POSITIVE LOGITS
     |
    0.17
    ãĢģ
    0.17
    ãĢįãĢĮ
    0.13
    ï¼īãĢģ
    0.13
     |↵
    0.12
     ·
    0.11
    |
    0.11
     âĶĤ
    0.11
    ]|[
    0.11
    0.11
    Activations Density 0.883%

    No Known Activations