© 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. 25598
    Prev
    Next
    INDEX
    Explanations

    69

    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
     Ing
    -0.11
    /compiler
    -0.10
    _units
    -0.10
    mint
    -0.10
    鼷
    -0.10
    OrCreate
    -0.10
    Authority
    -0.10
    lauf
    -0.10
     atrav
    -0.10
    ROME
    -0.10
    POSITIVE LOGITS
    eker
    0.11
    ing
    0.10
    izer
    0.09
    evin
    0.08
    ations
    0.08
    ming
    0.08
     symbol
    0.07
     Malone
    0.07
    ichel
    0.07
    ekt
    0.07
    Activations Density 0.025%

    No Known Activations