© 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. 28946
    Prev
    Next
    INDEX
    Explanations

    .png file extensions

    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
     mandatory
    -0.08
    atto
    -0.08
     tractor
    -0.07
    .Linked
    -0.07
    chn
    -0.07
    /trunk
    -0.07
     sacrifice
    -0.07
    ullo
    -0.07
     wirk
    -0.07
    Members
    -0.07
    POSITIVE LOGITS
     Hale
    0.11
    --[[
    0.11
     Sey
    0.11
     PIXEL
    0.11
    obo
    0.10
    undo
    0.10
    ghan
    0.10
     foregoing
    0.10
    elsing
    0.10
    andel
    0.10
    Activations Density 0.001%

    No Known Activations