© 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. 112114
    Prev
    Next
    INDEX
    Explanations

    age-specific identification of neoplasms

    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
    agt
    -0.11
    aden
    -0.09
     reordered
    -0.08
     gravy
    -0.08
    nak
    -0.08
    dana
    -0.08
    /reg
    -0.08
    upo
    -0.08
     Walsh
    -0.08
    ypes
    -0.07
    POSITIVE LOGITS
     tertiary
    0.11
    isex
    0.11
    anything
    0.10
    amo
    0.09
    wid
    0.09
     condemnation
    0.09
     inspiring
    0.09
     nas
    0.09
    enc
    0.09
    ZA
    0.09
    Activations Density 0.001%

    No Known Activations