© 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. 5644
    Prev
    Next
    INDEX
    Explanations

    ceiling light panels

    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
    fulness
    -0.10
    ched
    -0.08
    grounds
    -0.08
    leh
    -0.08
    weed
    -0.08
    house
    -0.08
    zeit
    -0.08
     Lis
    -0.08
     Sunset
    -0.08
    coe
    -0.08
    POSITIVE LOGITS
    -mounted
    0.16
    -high
    0.12
    alus
    0.11
    ed
    0.10
    -reaching
    0.10
    /footer
    0.10
    -ce
    0.10
     ABOVE
    0.10
    _pan
    0.10
    nut
    0.10
    Activations Density 0.023%

    No Known Activations