© 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. 17955
    Prev
    Next
    INDEX
    Explanations

    first followed by a noun

    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
     daddy
    -0.09
     hurry
    -0.09
    wand
    -0.08
    ç«ĭ
    -0.08
    ses
    -0.08
     Seriously
    -0.08
     shared
    -0.08
    izia
    -0.08
     Bes
    -0.08
     sang
    -0.08
    POSITIVE LOGITS
     thing
    0.20
    thing
    0.13
     reason
    0.13
     indication
    0.12
     things
    0.12
     person
    0.12
     few
    0.12
    Thing
    0.12
     syll
    0.12
     indications
    0.11
    Activations Density 0.034%

    No Known Activations