© 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. 7855
    Prev
    Next
    INDEX
    Explanations

    writing about something

    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
     brawl
    -0.08
     Weed
    -0.08
    anko
    -0.08
     Animator
    -0.08
    atz
    -0.08
    ereo
    -0.08
     footing
    -0.08
     spice
    -0.08
    .free
    -0.08
    alion
    -0.08
    POSITIVE LOGITS
     writing
    0.17
     Writing
    0.15
    Writing
    0.14
    writing
    0.13
     writings
    0.13
     write
    0.13
     wrote
    0.12
    Pad
    0.12
     Write
    0.12
    pad
    0.12
    Activations Density 0.021%

    No Known Activations