© 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. 6955
    Prev
    Next
    INDEX
    Explanations

    bodily fluids and secretions

    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
     ju
    -0.10
     juice
    -0.10
    away
    -0.10
     frequ
    -0.09
    igos
    -0.09
     juven
    -0.09
     Juice
    -0.09
     juvenile
    -0.09
    eger
    -0.09
     apprent
    -0.09
    POSITIVE LOGITS
    vore
    0.11
    uble
    0.10
    -filled
    0.10
     Hai
    0.10
    /o
    0.09
    ono
    0.09
    íĦ´
    0.09
    gue
    0.09
    esp
    0.09
    idity
    0.09
    Activations Density 0.002%

    No Known Activations