© 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. 47654
    Prev
    Next
    INDEX
    Explanations

    coloring and shading 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
     Glow
    -0.11
    enne
    -0.10
     Bark
    -0.10
     glow
    -0.09
     bids
    -0.09
     Sticky
    -0.09
     draggable
    -0.09
     semif
    -0.09
     perish
    -0.09
     Bas
    -0.09
    POSITIVE LOGITS
     coloring
    0.19
     Coloring
    0.18
     cray
    0.14
     Mandal
    0.14
     mand
    0.13
     Mand
    0.11
     Haram
    0.11
     Colo
    0.11
    iks
    0.10
    aut
    0.10
    Activations Density 0.115%

    No Known Activations