© 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. 28908
    Prev
    Next
    INDEX
    Explanations

    request or help

    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
     intern
    -0.09
    .Des
    -0.09
     Dep
    -0.09
     ::=
    -0.09
     Wyn
    -0.09
    ivery
    -0.08
     retr
    -0.08
     Dad
    -0.08
     Swagger
    -0.08
     mum
    -0.08
    POSITIVE LOGITS
    请
    0.17
     please
    0.17
    ï¼Į请
    0.16
     Please
    0.15
     seniors
    0.15
     esteemed
    0.14
     inconvenience
    0.13
    .Please
    0.13
    >Please
    0.13
    please
    0.13
    Activations Density 0.092%

    No Known Activations