© 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. 112078
    Prev
    Next
    INDEX
    Explanations

    Up the night, the odds, the fires

    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
    ishi
    -0.09
     Trem
    -0.08
     **
    -0.08
     RE
    -0.08
    bak
    -0.08
    Invocation
    -0.08
     Ori
    -0.08
    oval
    -0.07
    onic
    -0.07
    529
    -0.07
    POSITIVE LOGITS
    -of
    0.14
    InThe
    0.13
    ...',
    0.12
    -at
    0.11
    -to
    0.11
    -for
    0.11
    -with
    0.11
    /drivers
    0.11
    ..'
    0.11
    -the
    0.10
    Activations Density 0.657%

    No Known Activations