© 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. 15033
    Prev
    Next
    INDEX
    Explanations

    skin, muscle, and soft tissue

    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
     skin
    -0.39
     Skin
    -0.36
     skins
    -0.36
    Skin
    -0.32
    skin
    -0.31
    _skin
    -0.29
    skins
    -0.24
     skincare
    -0.21
    .skin
    -0.18
     dermat
    -0.18
    POSITIVE LOGITS
     Hair
    0.12
    Hair
    0.12
     hair
    0.11
    hair
    0.10
    ifa
    0.10
    arpa
    0.10
     veins
    0.10
     furniture
    0.09
     Dalton
    0.09
    hdr
    0.09
    Activations Density 0.244%

    No Known Activations