© 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. 32064
    Prev
    Next
    INDEX
    Explanations

    eyelids or eyebrows

    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
     Anchor
    -0.11
    å¾Ħ
    -0.11
    Anchor
    -0.10
    afen
    -0.09
     patent
    -0.09
    bery
    -0.09
    bote
    -0.08
     chimney
    -0.08
    éĶ
    -0.08
     uf
    -0.08
    POSITIVE LOGITS
    lian
    0.10
     reli
    0.10
     Berm
    0.10
    rog
    0.09
     eyeb
    0.09
     Jurassic
    0.09
     freaking
    0.09
     COUR
    0.08
     Rope
    0.08
    ITIONS
    0.08
    Activations Density 0.028%

    No Known Activations