© 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. 25696
    Prev
    Next
    INDEX
    Explanations

    saliva/salivary

    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
    oud
    -0.10
    ifr
    -0.08
     displ
    -0.08
     Jou
    -0.08
    /ns
    -0.08
     blurry
    -0.08
     nudity
    -0.08
     Chest
    -0.08
     amsterdam
    -0.08
    wers
    -0.08
    POSITIVE LOGITS
     lips
    0.15
     vowels
    0.12
     Cham
    0.11
     infinit
    0.11
     cham
    0.11
     patiently
    0.10
     porch
    0.10
     tantal
    0.10
     pave
    0.10
     receptors
    0.10
    Activations Density 0.005%

    No Known Activations