© 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. 28586
    Prev
    Next
    INDEX
    Explanations

    PG followed by FD or en

    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
     RPC
    -0.10
    æį®
    -0.10
    Lite
    -0.09
    riv
    -0.09
    UAL
    -0.09
    icularly
    -0.09
    ëħ
    -0.09
     bait
    -0.08
    rug
    -0.08
     Uh
    -0.08
    POSITIVE LOGITS
    cps
    0.10
    IMER
    0.10
    /pg
    0.10
    -rated
    0.09
    .TestTools
    0.09
     diploma
    0.09
    YTE
    0.09
    ucken
    0.09
    MEA
    0.08
    ullet
    0.08
    Activations Density 0.070%

    No Known Activations