© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48989
    Prev
    Next
    INDEX
    Explanations

    words ending with 'a' or names like Sark, Romeo, Sofoluwe

    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
    ka
    -0.21
    na
    -0.20
    l
    -0.19
    k
    -0.19
    b
    -0.19
    v
    -0.18
    nya
    -0.18
    ma
    -0.18
    m
    -0.17
    da
    -0.17
    POSITIVE LOGITS
    frica
    0.24
    issance
    0.22
    foon
    0.20
    ev
    0.19
    âĤ¬âĦ¢
    0.19
    eus
    0.18
    conda
    0.18
    ught
    0.18
    fter
    0.18
    ughty
    0.18
    Activations Density 1.543%

    No Known Activations