© 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. 30884
    Prev
    Next
    INDEX
    Explanations

    words following a comma

    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
     Elm
    -0.13
     Yates
    -0.12
    .nr
    -0.12
     Pere
    -0.11
    soever
    -0.11
    ~-
    -0.11
     Sprint
    -0.11
     ness
    -0.10
    ulance
    -0.10
     ÑĤо
    -0.10
    POSITIVE LOGITS
     which
    0.10
    Included
    0.08
     Hampton
    0.08
     there
    0.08
     Zucker
    0.08
    which
    0.07
     Another
    0.07
    there
    0.07
     Eden
    0.07
     what
    0.07
    Activations Density 0.023%

    No Known Activations