© 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. 116638
    Prev
    Next
    INDEX
    Explanations

    entitled, titled, or called

    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
    argon
    -0.12
     @[
    -0.11
     __(
    -0.10
     meas
    -0.10
     Sidebar
    -0.10
    <?=
    -0.10
    Ever
    -0.10
    /Main
    -0.10
    ingleton
    -0.10
     @$
    -0.10
    POSITIVE LOGITS
     titled
    0.55
     entitled
    0.53
     “
    0.36
     "
    0.34
    itled
    0.29
     ‘
    0.26
     called
    0.26
     (“
    0.24
     ”
    0.23
     âĢŀ
    0.23
    Activations Density 1.501%

    No Known Activations