© 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. 115300
    Prev
    Next
    INDEX
    Explanations

    before lunch

    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
    quiv
    -0.10
    agraph
    -0.08
     vanity
    -0.07
    acos
    -0.07
    icc
    -0.07
    agg
    -0.07
    rong
    -0.07
     gastr
    -0.07
     allot
    -0.07
     lest
    -0.07
    POSITIVE LOGITS
    yet
    0.13
     Haven
    0.12
     yet
    0.12
     figuring
    0.12
    react
    0.12
     reacting
    0.12
     Schw
    0.11
     formally
    0.11
    idl
    0.11
    iland
    0.11
    Activations Density 0.005%

    No Known Activations