© 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. 46686
    Prev
    Next
    INDEX
    Explanations

    differ in or from

    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
    ized
    -0.11
    izing
    -0.10
     mischief
    -0.10
    izador
    -0.10
    OOK
    -0.10
    izations
    -0.10
     Gilles
    -0.10
    eer
    -0.10
    tight
    -0.10
     tighter
    -0.10
    POSITIVE LOGITS
     greatly
    0.14
     markedly
    0.13
     sharply
    0.12
     significantly
    0.12
     substantially
    0.12
    ently
    0.12
    encing
    0.12
    enced
    0.12
     slightly
    0.11
     from
    0.11
    Activations Density 0.037%

    No Known Activations