© 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. 91170
    Prev
    Next
    INDEX
    Explanations

    strong argument could be made

    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
    cki
    -0.11
    bef
    -0.10
     Kenn
    -0.10
     Beacon
    -0.10
    fte
    -0.09
     Bucc
    -0.09
    acas
    -0.09
    rlen
    -0.09
     stead
    -0.09
     ank
    -0.09
    POSITIVE LOGITS
     можно
    0.24
     arguably
    0.21
     you
    0.19
     could
    0.17
     might
    0.16
     arg
    0.16
     Arg
    0.15
    Could
    0.15
    could
    0.14
    Arg
    0.14
    Activations Density 0.186%

    No Known Activations