© 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. 14613
    Prev
    Next
    INDEX
    Explanations

    content headers and labels

    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
     hur
    -0.09
    annotations
    -0.08
    igan
    -0.07
    aghetti
    -0.07
    istros
    -0.07
     Grande
    -0.07
    =%.
    -0.07
    nowled
    -0.07
    ì¹ĺ
    -0.07
    ifold
    -0.07
    POSITIVE LOGITS
    dating
    0.10
     suites
    0.10
     mobil
    0.10
     automáticamente
    0.10
    mob
    0.10
    _Tr
    0.09
    aket
    0.09
    games
    0.09
     Math
    0.09
    *Math
    0.09
    Activations Density 0.120%

    No Known Activations