© 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. 4437
    Prev
    Next
    INDEX
    Explanations

    say what

    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
     vit
    -0.10
     visibly
    -0.09
    ester
    -0.09
     believable
    -0.08
    chl
    -0.07
     Gle
    -0.07
    inel
    -0.07
     Adrian
    -0.07
     impressive
    -0.07
     measurable
    -0.07
    POSITIVE LOGITS
     Stamp
    0.11
    indo
    0.11
    stin
    0.10
     Fare
    0.10
     Decom
    0.10
    687
    0.10
    oter
    0.10
     <<-
    0.10
    bus
    0.10
    alic
    0.10
    Activations Density 0.002%

    No Known Activations