© 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. 90919
    Prev
    Next
    INDEX
    Explanations

    wheel and its related terms

    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
     envelopes
    -0.10
    dance
    -0.08
    QRST
    -0.08
    markt
    -0.08
     jab
    -0.08
     Tunnel
    -0.07
     punch
    -0.07
    omba
    -0.07
     tá»
    -0.07
     reopening
    -0.07
    POSITIVE LOGITS
     wheel
    0.27
     spokes
    0.26
    wheel
    0.25
     Wheel
    0.24
    Wheel
    0.23
     axle
    0.22
     wheels
    0.21
     Wheels
    0.20
     hub
    0.19
    -wheel
    0.18
    Activations Density 0.252%

    No Known Activations