© 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. 29053
    Prev
    Next
    INDEX
    Explanations

    Qt Toolkit or software licenses

    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
    outs
    -0.11
     buc
    -0.11
     sob
    -0.10
    _unsigned
    -0.10
     Mum
    -0.10
    `()
    -0.10
    hatt
    -0.10
     weak
    -0.10
    _bases
    -0.10
    *sp
    -0.10
    POSITIVE LOGITS
     Lester
    0.10
    eken
    0.08
     inaugural
    0.08
     Rosenberg
    0.08
    inder
    0.07
     vintage
    0.07
    loh
    0.07
    æĿ
    0.07
     faithful
    0.07
    epad
    0.07
    Activations Density 0.001%

    No Known Activations