© 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. 89214
    Prev
    Next
    INDEX
    Explanations

    chat prefixes

    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
    -pane
    -0.10
    quat
    -0.09
     prow
    -0.09
    nock
    -0.09
    afa
    -0.09
     âĸº
    -0.09
     /*----------------------------------------------------------------
    -0.08
    amente
    -0.08
    (TM
    -0.08
     Giz
    -0.08
    POSITIVE LOGITS
     again
    0.14
     proceeds
    0.11
     then
    0.11
     ultimately
    0.10
    Proceed
    0.10
     resumes
    0.10
     blush
    0.10
     later
    0.10
    åĨį
    0.10
     now
    0.10
    Activations Density 0.053%

    No Known Activations