© 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. 91092
    Prev
    Next
    INDEX
    Explanations

    times and durations

    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
    —to
    -0.11
    —one
    -0.11
    —including
    -0.11
    —who
    -0.11
    —in
    -0.11
    icol
    -0.10
     quint
    -0.10
    —a
    -0.10
    —not
    -0.10
    —for
    -0.10
    POSITIVE LOGITS
     Bast
    0.13
    incl
    0.10
     Fowler
    0.09
    eroon
    0.09
     dilig
    0.09
     Matte
    0.09
     flashing
    0.09
     faker
    0.09
     Expect
    0.09
     tob
    0.09
    Activations Density 0.012%

    No Known Activations