© 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. 50373
    Prev
    Next
    INDEX
    Explanations

    HTML document structure and tags

    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
     '
    -0.18
    'n
    -0.18
    'd
    -0.17
    '
    -0.17
    're
    -0.15
    's
    -0.14
    't
    -0.14
    'm
    -0.14
    ,'
    -0.14
    'll
    -0.13
    POSITIVE LOGITS
    ‘s
    0.13
    ãĢı
    0.12
     Tart
    0.11
    ’.↵↵
    0.11
     Orden
    0.10
    _()↵
    0.10
     \''
    0.10
    =\'
    0.10
    »↵↵
    0.10
     s
    0.10
    Activations Density 0.047%

    No Known Activations