© 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. 6233
    Prev
    Next
    INDEX
    Explanations

    writing journal entries

    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
    reas
    -0.11
    commons
    -0.09
     lingering
    -0.09
     conditioned
    -0.08
     egal
    -0.08
     infographic
    -0.08
     Sponsored
    -0.08
     Repeat
    -0.08
     satur
    -0.08
    óm
    -0.08
    POSITIVE LOGITS
     diary
    0.38
     journal
    0.33
     Diary
    0.32
     entries
    0.29
     journals
    0.28
     Entries
    0.26
    Entries
    0.23
    entries
    0.23
    journal
    0.22
     Journal
    0.22
    Activations Density 0.168%

    No Known Activations