© 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. 31006
    Prev
    Next
    INDEX
    Explanations

    associated documentation

    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
     comm
    -0.10
    alion
    -0.10
    /world
    -0.09
    Gro
    -0.09
    Ordered
    -0.08
     Dit
    -0.08
    gro
    -0.08
     caul
    -0.08
    tic
    -0.08
     Comm
    -0.08
    POSITIVE LOGITS
    acre
    0.11
     purs
    0.10
     EOS
    0.09
     corp
    0.09
    cheid
    0.09
    icl
    0.09
    éo
    0.09
     Lyon
    0.09
    _epochs
    0.09
    bearer
    0.09
    Activations Density 0.001%

    No Known Activations