© 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. 29039
    Prev
    Next
    INDEX
    Explanations

    twelve or 12

    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
    ī
    -0.11
    adia
    -0.11
     Hudson
    -0.11
     Spicer
    -0.11
    vider
    -0.10
     phi
    -0.10
    stadt
    -0.10
     HUD
    -0.10
    HUD
    -0.09
     Martian
    -0.09
    POSITIVE LOGITS
    12
    0.36
     twelve
    0.31
     Twelve
    0.28
     XII
    0.28
    012
    0.23
     December
    0.21
    December
    0.17
     december
    0.17
    112
    0.16
     dozen
    0.16
    Activations Density 0.372%

    No Known Activations