© 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. 31905
    Prev
    Next
    INDEX
    Explanations

    brake and motor vehicle systems

    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
    ish
    -0.08
    liness
    -0.08
     Keller
    -0.08
     Chow
    -0.08
     Compact
    -0.08
     Dj
    -0.08
    bread
    -0.08
    802
    -0.07
    erten
    -0.07
     piled
    -0.07
    POSITIVE LOGITS
    -equipped
    0.17
    -prop
    0.14
     engines
    0.13
    /engine
    0.13
     pedal
    0.12
     motors
    0.12
     sque
    0.12
     propel
    0.12
     system
    0.12
    less
    0.11
    Activations Density 0.149%

    No Known Activations