© 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. 90299
    Prev
    Next
    INDEX
    Explanations

    kilometers and similar measurements

    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
    tte
    -0.10
     concession
    -0.10
     Bookmark
    -0.08
    unders
    -0.08
    arah
    -0.08
    arak
    -0.08
    uto
    -0.08
    iest
    -0.08
     Catal
    -0.08
    amen
    -0.08
    POSITIVE LOGITS
    patrick
    0.14
    lick
    0.14
    odal
    0.13
     kil
    0.12
    oby
    0.12
    crease
    0.11
    ometer
    0.11
    minster
    0.11
    ambi
    0.11
    ometers
    0.11
    Activations Density 0.022%

    No Known Activations