© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31663
    Prev
    Next
    INDEX
    Explanations

    touches

    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
     industri
    -0.12
    unker
    -0.11
     trot
    -0.10
     masculinity
    -0.10
     Farrell
    -0.10
     squat
    -0.10
    iegel
    -0.10
    preview
    -0.10
     perc
    -0.10
    graphic
    -0.10
    POSITIVE LOGITS
     touching
    0.15
     Touch
    0.14
     touch
    0.14
     hair
    0.13
     touchscreen
    0.12
     touches
    0.12
    hair
    0.12
    touch
    0.11
     touched
    0.11
     finger
    0.11
    Activations Density 0.017%

    No Known Activations