© 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. 31714
    Prev
    Next
    INDEX
    Explanations

    um, unsigned, UM, typeof, Email, shell

    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
     THESE
    -0.11
     Blanco
    -0.11
    LineWidth
    -0.11
    agues
    -0.11
    ertest
    -0.11
    UTO
    -0.11
    íĮ
    -0.11
     //~
    -0.10
    issant
    -0.10
    yan
    -0.10
    POSITIVE LOGITS
     Advent
    0.09
    ...
    0.09
    ein
    0.08
    m
    0.07
    ,
    0.07
     Advanced
    0.07
    -th
    0.07
     casing
    0.07
     regress
    0.07
    azu
    0.07
    Activations Density 0.001%

    No Known Activations