© 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. 17420
    Prev
    Next
    INDEX
    Explanations

    causes tens

    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
    iou
    -0.10
    ninger
    -0.10
     firstly
    -0.10
    czy
    -0.10
    ï¼Į并
    -0.09
     nowadays
    -0.09
    eger
    -0.09
     kho
    -0.09
     although
    -0.09
    ect
    -0.08
    POSITIVE LOGITS
     Voll
    0.11
     reim
    0.10
     also
    0.10
    >;
    0.09
     Gallagher
    0.09
     Bik
    0.09
    also
    0.09
     ARCH
    0.09
     też
    0.09
     também
    0.09
    Activations Density 0.019%

    No Known Activations