© 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. 27427
    Prev
    Next
    INDEX
    Explanations

    liter and literature

    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
    dest
    -0.09
    engan
    -0.08
     triang
    -0.08
    mour
    -0.07
     parenthesis
    -0.07
    tri
    -0.07
    Env
    -0.07
     Env
    -0.07
     trilogy
    -0.07
    riday
    -0.07
    POSITIVE LOGITS
     polite
    0.11
    ally
    0.11
    azer
    0.10
    ality
    0.10
    озв
    0.10
     att
    0.10
     Baron
    0.10
     Shed
    0.10
    isan
    0.10
    @Web
    0.10
    Activations Density 0.001%

    No Known Activations