© 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. 112550
    Prev
    Next
    INDEX
    Explanations

    Names of companies or products

    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
     Rp
    -0.12
     intox
    -0.11
    chimp
    -0.11
    oad
    -0.11
    orch
    -0.11
    avez
    -0.10
    ombine
    -0.10
    ">&#
    -0.10
    endar
    -0.10
     redeem
    -0.10
    POSITIVE LOGITS
    —an
    0.10
    —the
    0.09
    —a
    0.09
     esteemed
    0.09
     ours
    0.08
     aka
    0.08
    ®,
    0.07
    ++.
    0.07
     meticulously
    0.07
    <\/
    0.06
    Activations Density 0.383%

    No Known Activations