© 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. 28982
    Prev
    Next
    INDEX
    Explanations

    call or broadcasting

    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
    ouro
    -0.12
    angep
    -0.11
    Gap
    -0.11
    (comp
    -0.11
    edd
    -0.11
    _SF
    -0.10
    ownership
    -0.10
    quis
    -0.10
    (sf
    -0.10
     Daily
    -0.10
    POSITIVE LOGITS
     insertion
    0.08
    439
    0.08
     graduated
    0.08
     Fond
    0.07
    ault
    0.07
     singleton
    0.07
     objs
    0.07
     Gam
    0.07
     unb
    0.07
     interns
    0.07
    Activations Density 0.001%

    No Known Activations