© 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. 3843
    Prev
    Next
    INDEX
    Explanations

    oral cavity

    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
     Consum
    -0.11
    inea
    -0.10
     ear
    -0.09
    rick
    -0.09
    /moment
    -0.08
     consum
    -0.08
     hij
    -0.08
    ments
    -0.08
    fan
    -0.08
     meth
    -0.08
    POSITIVE LOGITS
     cavity
    0.12
     utilized
    0.10
     bouncing
    0.10
    .uf
    0.10
     plateau
    0.10
    accordion
    0.10
     FORCE
    0.09
    -only
    0.09
    uve
    0.09
    /arm
    0.09
    Activations Density 0.024%

    No Known Activations