© 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. 6632
    Prev
    Next
    INDEX
    Explanations

    implied, years, license

    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
     sup
    -0.09
     lat
    -0.08
    iten
    -0.08
     altern
    -0.08
    icit
    -0.08
    VN
    -0.08
     dele
    -0.08
     recipro
    -0.08
    ural
    -0.08
     deleg
    -0.08
    POSITIVE LOGITS
     encount
    0.11
     Leer
    0.10
     Pence
    0.10
     conse
    0.10
     admon
    0.10
    udy
    0.10
     Ung
    0.10
    /format
    0.10
    opup
    0.09
    unter
    0.09
    Activations Density 0.005%

    No Known Activations