© 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. 28876
    Prev
    Next
    INDEX
    Explanations

    value followed by number or comment

    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
     LUA
    -0.10
     Bomb
    -0.10
     Crane
    -0.09
    unpack
    -0.09
    lap
    -0.09
     uncert
    -0.09
     grown
    -0.09
    arie
    -0.08
     Editorial
    -0.08
     Secondly
    -0.08
    POSITIVE LOGITS
    obil
    0.10
    iska
    0.10
     Slater
    0.10
     Kam
    0.10
     delegate
    0.10
     rest
    0.09
     Gardens
    0.09
    ills
    0.09
    rico
    0.09
     replacements
    0.09
    Activations Density 0.018%

    No Known Activations