© 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. 6730
    Prev
    Next
    INDEX
    Explanations

    states or actions

    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
    unset
    -0.11
    SetName
    -0.10
    /Dk
    -0.10
    ovah
    -0.10
    spect
    -0.10
    /GL
    -0.10
    echa
    -0.10
     debounce
    -0.10
    chez
    -0.10
    ://
    -0.09
    POSITIVE LOGITS
    Ĵ
    0.07
    ï
    0.06
    yyyy
    0.06
     "
    0.06
    (
    0.06
    itive
    0.06
    âĢij
    0.06
     (
    0.06
     Trident
    0.06
     balcony
    0.06
    Activations Density 1.387%

    No Known Activations