© 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. 116202
    Prev
    Next
    INDEX
    Explanations

    names ending in ey, oy, ay

    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
    edBy
    -0.12
     artificially
    -0.11
    crud
    -0.10
    ystone
    -0.10
    ipation
    -0.10
    viar
    -0.10
     Tent
    -0.09
    .Gray
    -0.09
    ég
    -0.09
    metric
    -0.09
    POSITIVE LOGITS
    otes
    0.12
    ophobic
    0.10
    ote
    0.10
     hab
    0.09
     apparent
    0.08
    ppy
    0.08
    enis
    0.08
     sluggish
    0.08
    Oper
    0.08
     present
    0.08
    Activations Density 0.022%

    No Known Activations