© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5870
    Prev
    Next
    INDEX
    Explanations

    file formats (PDF, XML, HTML)

    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
    ole
    -0.08
    arna
    -0.08
     overwhelming
    -0.07
    ends
    -0.07
     ani
    -0.07
    line
    -0.07
    wide
    -0.06
     Wahl
    -0.06
     Brewer
    -0.06
    ories
    -0.06
    POSITIVE LOGITS
    ,application
    0.13
    rpc
    0.12
    webtoken
    0.11
    .twig
    0.11
    hoot
    0.11
    )._
    0.11
    -License
    0.10
    995
    0.10
    hurst
    0.10
    arian
    0.10
    Activations Density 0.296%

    No Known Activations