© 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. 49255
    Prev
    Next
    INDEX
    Explanations

    cheap, cheaper, cheapest

    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
    roi
    -0.09
     Royale
    -0.09
     Christoph
    -0.09
    edb
    -0.08
    ffa
    -0.08
     Fortune
    -0.08
    ledged
    -0.08
    ingle
    -0.08
    UPS
    -0.08
    led
    -0.08
    POSITIVE LOGITS
    /free
    0.19
    ening
    0.16
    (er
    0.15
    ened
    0.13
    -priced
    0.13
     priced
    0.13
     plentiful
    0.12
     prices
    0.12
     price
    0.12
    ens
    0.12
    Activations Density 0.011%

    No Known Activations