© 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. 33514
    Prev
    Next
    INDEX
    Explanations

    initialisms and abbreviations

    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
    iqu
    -0.12
    istic
    -0.12
    iska
    -0.11
    cash
    -0.10
    Äį
    -0.10
    acco
    -0.10
    crypt
    -0.10
    reck
    -0.10
    onet
    -0.10
    catch
    -0.10
    POSITIVE LOGITS
    ollectors
    0.16
    ording
    0.13
    ourt
    0.12
    raft
    0.12
    erule
    0.12
    ivicrm
    0.11
    lean
    0.11
    adden
    0.11
    ron
    0.10
    ityEngine
    0.10
    Activations Density 2.366%

    No Known Activations