© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18597
    Prev
    Next
    INDEX
    Explanations

    hair grooming

    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
    Negative Logits
     Lens
    -0.10
     ESC
    -0.10
     Sne
    -0.10
     bud
    -0.10
     scripted
    -0.10
     lipstick
    -0.10
     Hover
    -0.10
     cheek
    -0.09
     Stealth
    -0.09
     Whisper
    -0.09
    POSITIVE LOGITS
     knots
    0.16
     grooming
    0.15
     comb
    0.14
     tangled
    0.14
     yarn
    0.13
     conditioner
    0.13
     Knot
    0.13
     knot
    0.12
     det
    0.12
     hair
    0.12
    Activations Density 0.093%

    No Known Activations