© 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. 47113
    Prev
    Next
    INDEX
    Explanations

    flat things and concepts

    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
    +S
    -0.10
     ure
    -0.09
     claw
    -0.09
    caff
    -0.09
     rop
    -0.08
     vag
    -0.08
    alta
    -0.08
     bust
    -0.08
     Fairfield
    -0.08
    Cluster
    -0.08
    POSITIVE LOGITS
    .Flat
    0.20
     panc
    0.17
     Flat
    0.17
     flat
    0.17
    Flat
    0.17
    flat
    0.16
     flatt
    0.15
    -flat
    0.15
     Panc
    0.14
     flatten
    0.13
    Activations Density 0.056%

    No Known Activations