© 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. 50617
    Prev
    Next
    INDEX
    Explanations

    type or kind

    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
    azo
    -0.10
     Müller
    -0.09
    Beh
    -0.08
     SOME
    -0.08
     literally
    -0.08
     anom
    -0.08
    CARD
    -0.08
    .Pe
    -0.08
    (orig
    -0.08
    +%
    -0.08
    POSITIVE LOGITS
     attracted
    0.20
     attracts
    0.18
     attract
    0.18
     typical
    0.18
     attracting
    0.18
     types
    0.17
     typically
    0.16
    typ
    0.16
     type
    0.16
     Typically
    0.14
    Activations Density 0.066%

    No Known Activations