© 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. 116983
    Prev
    Next
    INDEX
    Explanations

    touch

    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
    enk
    -0.09
     Depart
    -0.09
     depart
    -0.09
     confidently
    -0.09
    arin
    -0.09
    anne
    -0.09
     richer
    -0.09
    Sdk
    -0.09
     pivot
    -0.08
     Nude
    -0.08
    POSITIVE LOGITS
     poking
    0.13
     initially
    0.13
     touching
    0.12
     scratching
    0.12
     scratch
    0.11
     touch
    0.11
    -touch
    0.11
     touches
    0.10
     Touch
    0.10
     touched
    0.10
    Activations Density 0.002%

    No Known Activations