© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117251
    Prev
    Next
    INDEX
    Explanations

    tan, brown, green 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
    æį
    -0.09
     Blue
    -0.09
    less
    -0.09
     flaming
    -0.09
    å¼ı
    -0.09
     atop
    -0.09
     Gold
    -0.08
    ico
    -0.08
     sub
    -0.08
    hub
    -0.08
    POSITIVE LOGITS
    -colored
    0.29
     colored
    0.20
    èī²
    0.18
    ìĥī
    0.17
    -color
    0.17
     coloured
    0.17
    -col
    0.15
     color
    0.15
     colour
    0.13
    -tone
    0.13
    Activations Density 0.182%

    No Known Activations