© 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. 25769
    Prev
    Next
    INDEX
    Explanations

    that is,

    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
    atio
    -0.09
     Fritz
    -0.08
     yet
    -0.08
    fen
    -0.08
    Yet
    -0.08
     Yet
    -0.08
    omo
    -0.08
    fer
    -0.08
     lud
    -0.08
    depend
    -0.07
    POSITIVE LOGITS
    immel
    0.12
    ä¹Ī
    0.11
    osi
    0.11
    osite
    0.10
    prech
    0.10
    opers
    0.10
     Pert
    0.10
     sotto
    0.10
    efore
    0.10
     Matcher
    0.10
    Activations Density 0.011%

    No Known Activations