© 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. 47688
    Prev
    Next
    INDEX
    Explanations

    speed and direction

    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
     explos
    -0.11
    å¡
    -0.11
     hij
    -0.10
     soluble
    -0.10
    olin
    -0.10
     Battles
    -0.10
     Hij
    -0.10
     chute
    -0.09
    yne
    -0.09
    elas
    -0.09
    POSITIVE LOGITS
     speed
    0.26
     speeds
    0.24
     speeding
    0.22
    -speed
    0.21
     Speed
    0.21
     SPEED
    0.20
    speed
    0.19
    peed
    0.19
    Speed
    0.18
    (speed
    0.17
    Activations Density 0.071%

    No Known Activations