© 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. 90988
    Prev
    Next
    INDEX
    Explanations

    way to, help would, supposed to

    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
     folks
    -0.13
     caveat
    -0.11
     whereby
    -0.11
     caval
    -0.10
     afforded
    -0.09
     contentious
    -0.09
     disparate
    -0.09
    +++
    -0.09
     Asi
    -0.09
     purported
    -0.09
    POSITIVE LOGITS
     knex
    0.19
     exe
    0.14
     ecs
    0.14
     complet
    0.13
     reve
    0.13
     acess
    0.13
     tomar
    0.12
     farther
    0.12
     ness
    0.12
     sucess
    0.12
    Activations Density 1.076%

    No Known Activations