© 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. 112295
    Prev
    Next
    INDEX
    Explanations

    licenses and code snippets

    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
    /=
    -0.12
    isman
    -0.11
    none
    -0.10
    http
    -0.10
    {'
    -0.10
    ropa
    -0.10
    first
    -0.10
    ulet
    -0.10
    jsc
    -0.09
    igon
    -0.09
    POSITIVE LOGITS
    rtype
    0.11
    !:
    0.10
     Buckley
    0.09
    ï½¥
    0.08
    ////
    0.08
    Raster
    0.08
     desp
    0.08
    ,:,:
    0.08
    /:
    0.08
     Avery
    0.08
    Activations Density 0.394%

    No Known Activations