© 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. 113728
    Prev
    Next
    INDEX
    Explanations

    The Field of the Invention

    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
     Elliott
    -0.09
    Statement
    -0.08
     sidel
    -0.08
     classy
    -0.08
    åĪ©
    -0.08
     hardcoded
    -0.08
     libertine
    -0.07
     Bern
    -0.07
     arity
    -0.07
    keley
    -0.07
    POSITIVE LOGITS
    ____
    0.11
    aders
    0.11
    ___
    0.11
    Translations
    0.10
     __(
    0.10
    algo
    0.10
    .xhtml
    0.10
     Kosten
    0.10
    ader
    0.10
    enga
    0.10
    Activations Density 0.022%

    No Known Activations