© 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. 31322
    Prev
    Next
    INDEX
    Explanations

    one of

    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
     stuff
    -0.10
     Stuff
    -0.10
    obi
    -0.09
    _stuff
    -0.09
    Stuff
    -0.08
    baz
    -0.08
     semi
    -0.08
    Iss
    -0.08
    achel
    -0.08
     misc
    -0.07
    POSITIVE LOGITS
     Cas
    0.11
    -square
    0.10
    anan
    0.10
     Reynolds
    0.10
    plan
    0.10
     to
    0.10
    Protocol
    0.10
    thon
    0.10
    Extreme
    0.10
     conjug
    0.10
    Activations Density 0.008%

    No Known Activations