© 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. 88842
    Prev
    Next
    INDEX
    Explanations

    licking or wiping body parts

    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
    OTA
    -0.11
    NM
    -0.11
     Injectable
    -0.11
    ount
    -0.11
     wrest
    -0.10
     Punch
    -0.10
     Tul
    -0.10
    shi
    -0.09
     ver
    -0.09
     pier
    -0.09
    POSITIVE LOGITS
     thumb
    0.27
     thumbs
    0.21
     Thumb
    0.18
     tongue
    0.18
     licking
    0.17
     wiping
    0.17
     finger
    0.16
    Thumb
    0.16
     wipe
    0.16
    thumb
    0.15
    Activations Density 0.087%

    No Known Activations