© 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. 90948
    Prev
    Next
    INDEX
    Explanations

    errors are solely

    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
     Oliv
    -0.11
     sway
    -0.10
    ushima
    -0.10
    imore
    -0.10
    ols
    -0.10
    cry
    -0.09
    owi
    -0.09
     Aly
    -0.09
    eldon
    -0.09
     sprink
    -0.09
    POSITIVE LOGITS
     Coh
    0.10
    lice
    0.10
     errors
    0.09
     PURE
    0.09
     confusing
    0.09
    adge
    0.09
    uhan
    0.09
     coherent
    0.08
     coherence
    0.08
    FUNC
    0.08
    Activations Density 0.002%

    No Known Activations