© 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. 17804
    Prev
    Next
    INDEX
    Explanations

    story collections and anthologies

    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
    idy
    -0.10
     Registers
    -0.10
     spectacle
    -0.10
     preempt
    -0.10
     Forg
    -0.10
     Distrib
    -0.09
    Bars
    -0.09
     counters
    -0.09
    registers
    -0.09
     collapsed
    -0.09
    POSITIVE LOGITS
     anthology
    0.30
     tales
    0.29
     stories
    0.27
     Tales
    0.24
     vign
    0.24
     Stories
    0.22
     collection
    0.22
     shorts
    0.22
    stories
    0.21
    Stories
    0.20
    Activations Density 0.699%

    No Known Activations