© 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. 49615
    Prev
    Next
    INDEX
    Explanations

    .cpp, manager, title, rule, data, numpy

    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
    gor
    -0.10
    sonian
    -0.10
    ner
    -0.10
    piel
    -0.10
    slash
    -0.10
    urge
    -0.10
    cher
    -0.09
    ser
    -0.09
    lys
    -0.09
    achie
    -0.09
    POSITIVE LOGITS
    riz
    0.10
    ebb
    0.10
     goodness
    0.09
    enso
    0.09
    yb
    0.08
    MZ
    0.08
    Hur
    0.08
     Sicher
    0.08
    clid
    0.08
    eor
    0.08
    Activations Density 0.275%

    No Known Activations