© 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. 30163
    Prev
    Next
    INDEX
    Explanations

    curling, sleeping, resting

    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
     intox
    -0.11
    rops
    -0.11
    .bel
    -0.10
    udeau
    -0.10
    esk
    -0.10
     tread
    -0.10
     cocktails
    -0.10
    empo
    -0.10
    pper
    -0.09
    iswa
    -0.09
    POSITIVE LOGITS
     curled
    0.28
     curl
    0.23
     Curl
    0.22
     curls
    0.18
     tucked
    0.16
     nestled
    0.14
     cudd
    0.14
    curl
    0.12
     nest
    0.12
     curly
    0.11
    Activations Density 0.059%

    No Known Activations