© 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. 116547
    Prev
    Next
    INDEX
    Explanations

    Platform Guide

    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
    aky
    -0.11
     Zam
    -0.11
    rint
    -0.10
     Interfaces
    -0.09
    olio
    -0.09
    Ãłn
    -0.09
    usters
    -0.09
    amina
    -0.09
    CSI
    -0.09
     vol
    -0.09
    POSITIVE LOGITS
     Grip
    0.09
    ocker
    0.09
     tame
    0.09
     nj
    0.09
     lesser
    0.09
     Ner
    0.08
     ли
    0.08
     Jah
    0.08
    /TR
    0.08
     enjo
    0.08
    Activations Density 0.001%

    No Known Activations