© 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. 25477
    Prev
    Next
    INDEX
    Explanations

    color or colour variations

    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
    /left
    -0.10
     Doch
    -0.09
     eventual
    -0.09
     ancest
    -0.09
    tas
    -0.09
    endl
    -0.09
     Extras
    -0.09
    -turned
    -0.08
    /shared
    -0.08
    /report
    -0.08
    POSITIVE LOGITS
    /color
    0.15
    atura
    0.15
    less
    0.15
     scheme
    0.14
    ation
    0.13
    ific
    0.13
    -wise
    0.12
    ized
    0.12
     schemes
    0.12
    ization
    0.12
    Activations Density 0.029%

    No Known Activations