© 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. 7687
    Prev
    Next
    INDEX
    Explanations

    fictional narrative and hypothetical scenarios

    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
     Webster
    -0.09
     robbed
    -0.08
     incorporated
    -0.08
    uje
    -0.08
    ucks
    -0.08
     Communities
    -0.08
     dared
    -0.08
     thumb
    -0.08
     Wan
    -0.08
     dov
    -0.08
    POSITIVE LOGITS
     fict
    0.16
     fictional
    0.15
     depicted
    0.13
     hypothetical
    0.13
     simulated
    0.11
     depiction
    0.11
     assumed
    0.11
    anan
    0.11
     imagined
    0.11
     presumed
    0.10
    Activations Density 0.001%

    No Known Activations