© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27319
    Prev
    Next
    INDEX
    Explanations

    paths and directories

    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
    comma
    -0.07
    gorith
    -0.07
     https
    -0.07
     attract
    -0.06
     favourable
    -0.06
     Gol
    -0.06
     illusion
    -0.06
     age
    -0.06
    Unnamed
    -0.06
    674
    -0.06
    POSITIVE LOGITS
    ourg
    0.15
     :↵↵↵↵
    0.12
    Ë
    0.12
     crushing
    0.12
    -world
    0.11
    rade
    0.11
    <dd
    0.11
    usr
    0.11
     Signs
    0.10
    .au
    0.10
    Activations Density 0.156%

    No Known Activations