© 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. 16946
    Prev
    Next
    INDEX
    Explanations

    Microsoft, Research, About, Fight

    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
     flick
    -0.08
     sal
    -0.08
    arb
    -0.07
    opi
    -0.07
     flirt
    -0.07
    _COMMIT
    -0.07
     chor
    -0.06
     allot
    -0.06
     fluid
    -0.06
    asser
    -0.06
    POSITIVE LOGITS
    ugi
    0.12
     Laur
    0.11
    ledge
    0.11
    achie
    0.11
    antas
    0.11
    mr
    0.11
    pk
    0.11
     Pets
    0.11
     squirrel
    0.10
    Misc
    0.10
    Activations Density 0.025%

    No Known Activations