© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 15549
    Prev
    Next
    INDEX
    Explanations

    Syria on, game against, evening saying

    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
    —but
    -0.15
    —which
    -0.14
    —and
    -0.13
    ,and
    -0.13
    —it
    -0.13
    —they
    -0.12
    —are
    -0.12
    –and
    -0.11
    ・・
    -0.11
    —is
    -0.11
    POSITIVE LOGITS
     ,
    0.11
    ,rp
    0.11
    (),
    0.10
    _,
    0.09
    alli
    0.09
    ilen
    0.09
    ,assign
    0.09
    aje
    0.08
    REEN
    0.08
    ajs
    0.08
    Activations Density 0.108%

    No Known Activations