© 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. 16578
    Prev
    Next
    INDEX
    Explanations

    formal scientific technical

    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
    /Branch
    -0.10
     experiences
    -0.09
    experience
    -0.09
     Gos
    -0.09
     Stories
    -0.09
    ylie
    -0.09
    oins
    -0.08
    ulen
    -0.08
     incons
    -0.08
    vert
    -0.08
    POSITIVE LOGITS
     scientifically
    0.30
     scientific
    0.28
    scientific
    0.24
     technical
    0.23
     formal
    0.21
     technically
    0.21
     formally
    0.20
     science
    0.19
     Scientific
    0.19
    technical
    0.19
    Activations Density 0.543%

    No Known Activations