© 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. 32133
    Prev
    Next
    INDEX
    Explanations

    sweeping, rolling, or circular movements

    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
     unfavor
    -0.09
     conscience
    -0.09
    /response
    -0.09
     Boots
    -0.09
     polluted
    -0.09
     Caller
    -0.09
     incremented
    -0.09
     Boot
    -0.09
     sweat
    -0.09
    mast
    -0.09
    POSITIVE LOGITS
     strokes
    0.19
     techniques
    0.19
     gentle
    0.18
     movements
    0.18
     repetitive
    0.16
     gestures
    0.16
     motions
    0.16
     repetition
    0.15
     repeated
    0.15
     repetitions
    0.14
    Activations Density 0.029%

    No Known Activations