© 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. 112501
    Prev
    Next
    INDEX
    Explanations

    skin and related tissues

    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
     surrounds
    -0.11
     ceiling
    -0.10
     tail
    -0.10
     surround
    -0.10
    (PC
    -0.10
     walls
    -0.10
     seats
    -0.10
    .getContentPane
    -0.09
     disag
    -0.09
    stem
    -0.09
    POSITIVE LOGITS
     skin
    0.18
     Skin
    0.18
    Skin
    0.17
     Surface
    0.17
     surface
    0.17
     scars
    0.15
     dermat
    0.15
     muscle
    0.14
     patches
    0.14
     tattoo
    0.14
    Activations Density 0.264%

    No Known Activations