© 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. 33482
    Prev
    Next
    INDEX
    Explanations

    sexuality, benchmarks, precision, League

    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
    a
    -0.18
    /gui
    -0.11
    fed
    -0.10
    c
    -0.10
    e
    -0.10
    eve
    -0.10
    f
    -0.10
    fab
    -0.10
    fang
    -0.10
    rome
    -0.09
    POSITIVE LOGITS
    s
    0.22
    es
    0.19
    tings
    0.14
    ting
    0.13
    tlement
    0.11
    imately
    0.11
    ty
    0.10
    sar
    0.10
    sheets
    0.10
    sampling
    0.10
    Activations Density 0.001%

    No Known Activations