© 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. 89237
    Prev
    Next
    INDEX
    Explanations

    the one

    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
    quist
    -0.11
    nek
    -0.10
     thereof
    -0.09
    mente
    -0.09
    aa
    -0.09
    versions
    -0.09
    ius
    -0.09
    lew
    -0.09
    bat
    -0.09
     Exact
    -0.09
    POSITIVE LOGITS
     true
    0.13
     remaining
    0.13
     TRUE
    0.12
    th
    0.11
     exception
    0.11
     eyed
    0.11
     substantive
    0.10
     truly
    0.10
     responsible
    0.10
     place
    0.10
    Activations Density 0.029%

    No Known Activations