© 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. 91627
    Prev
    Next
    INDEX
    Explanations

    rolls off tongues

    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
     Pell
    -0.10
     Dar
    -0.09
     Hog
    -0.09
     attachments
    -0.09
     Darwin
    -0.09
    itra
    -0.09
     Cop
    -0.09
     wrench
    -0.08
     blitz
    -0.08
     minut
    -0.08
    POSITIVE LOGITS
     tongue
    0.21
     tongues
    0.18
     lips
    0.16
     Tong
    0.15
     coating
    0.12
     coated
    0.11
     licking
    0.11
     licked
    0.11
     tasted
    0.11
    .ac
    0.10
    Activations Density 0.005%

    No Known Activations