© 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. 33267
    Prev
    Next
    INDEX
    Explanations

    license and warranty

    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
    ania
    -0.09
    ogo
    -0.09
    ubb
    -0.09
     prox
    -0.08
    uma
    -0.08
     Lucia
    -0.08
     fatt
    -0.08
    engo
    -0.08
     Lara
    -0.08
     explos
    -0.08
    POSITIVE LOGITS
    Fld
    0.10
    pie
    0.10
     Gio
    0.10
    agen
    0.10
     *__
    0.09
     Lorem
    0.09
    illet
    0.09
    .ALL
    0.09
     perme
    0.09
     Gros
    0.09
    Activations Density 0.002%

    No Known Activations