© 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. 48660
    Prev
    Next
    INDEX
    Explanations

    cross compound words

    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
     Hoover
    -0.09
    reck
    -0.08
     trunk
    -0.08
    adora
    -0.08
     Gardner
    -0.08
    asion
    -0.08
     trace
    -0.08
    ardy
    -0.08
    zione
    -0.08
    itized
    -0.07
    POSITIVE LOGITS
    roads
    0.17
    (es
    0.16
    bow
    0.14
    -legged
    0.14
    fire
    0.13
    bones
    0.13
    -sectional
    0.12
    -eyed
    0.12
    -over
    0.11
    word
    0.11
    Activations Density 0.020%

    No Known Activations