© 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. 113515
    Prev
    Next
    INDEX
    Explanations

    light touches and brushing

    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
    orz
    -0.14
     jointly
    -0.11
    vre
    -0.10
     Mats
    -0.10
     skew
    -0.10
     respectively
    -0.09
    upy
    -0.09
     forever
    -0.09
     AFTER
    -0.09
     patiently
    -0.09
    POSITIVE LOGITS
     accidentally
    0.14
     sensitive
    0.14
     accidental
    0.13
     touched
    0.12
     touch
    0.12
     briefly
    0.11
     inadvertently
    0.11
    -touch
    0.11
     brushed
    0.11
     lightly
    0.11
    Activations Density 0.006%

    No Known Activations