© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90419
    Prev
    Next
    INDEX
    Explanations

    ) phrases

    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
     Burr
    -0.11
    s
    -0.10
     imm
    -0.10
    663
    -0.10
     Gir
    -0.09
     deflect
    -0.09
    sar
    -0.09
     apprec
    -0.09
    tsy
    -0.09
    side
    -0.09
    POSITIVE LOGITS
     Kosten
    0.10
     Reed
    0.09
     exhaust
    0.09
    esor
    0.09
    wal
    0.09
    wor
    0.08
    endl
    0.08
     NOTHING
    0.08
    emory
    0.08
     smoke
    0.08
    Activations Density 0.250%

    No Known Activations