© 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. 30738
    Prev
    Next
    INDEX
    Explanations

    written stories and prose

    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
     Dawson
    -0.12
    /info
    -0.10
    oir
    -0.10
     lookout
    -0.09
     Victim
    -0.09
    nee
    -0.09
    mime
    -0.09
     Vulkan
    -0.09
     defenses
    -0.09
    tru
    -0.09
    POSITIVE LOGITS
     writing
    0.15
     written
    0.14
     prose
    0.14
    -writing
    0.14
     scenario
    0.13
    writing
    0.13
     stories
    0.13
     story
    0.13
     imagined
    0.13
    -written
    0.13
    Activations Density 0.054%

    No Known Activations