© 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. 5954
    Prev
    Next
    INDEX
    Explanations

    some, others, other, three, half

    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
     Mund
    -0.11
     Moff
    -0.10
     Castillo
    -0.09
    utta
    -0.09
    iving
    -0.09
     Ney
    -0.09
    wyn
    -0.09
     Fletcher
    -0.09
    enga
    -0.09
     Wyn
    -0.09
    POSITIVE LOGITS
     Gi
    0.09
    eci
    0.09
    erm
    0.09
    scar
    0.09
     else
    0.08
    omm
    0.08
    bread
    0.08
     Pear
    0.08
    ento
    0.08
    ock
    0.08
    Activations Density 0.150%

    No Known Activations