© 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. 7303
    Prev
    Next
    INDEX
    Explanations

    shades of colors

    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
    etus
    -0.11
     stil
    -0.10
     ìĭ
    -0.09
     twitch
    -0.09
    tid
    -0.09
     Extras
    -0.09
     pis
    -0.09
     fert
    -0.09
    ruc
    -0.09
    icc
    -0.08
    POSITIVE LOGITS
     shades
    0.20
     Degrees
    0.17
     hues
    0.17
     shading
    0.16
     degrees
    0.16
     tones
    0.16
     Shades
    0.15
     colors
    0.15
     gray
    0.15
     shade
    0.14
    Activations Density 0.014%

    No Known Activations