© 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. 26317
    Prev
    Next
    INDEX
    Explanations

    literal meaning or intensifier

    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
    rome
    -0.09
     chiefly
    -0.09
    petto
    -0.09
    -SA
    -0.09
    croft
    -0.08
    wish
    -0.08
    room
    -0.08
    ç¤
    -0.08
     firmly
    -0.08
    -chat
    -0.08
    POSITIVE LOGITS
     literal
    0.21
     Literal
    0.18
     literally
    0.17
    -minded
    0.16
    literal
    0.15
    Literal
    0.14
     interpretation
    0.14
     minded
    0.13
    ized
    0.13
    ism
    0.13
    Activations Density 0.012%

    No Known Activations