© 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. 6145
    Prev
    Next
    INDEX
    Explanations

    benign

    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
    tant
    -0.10
    cw
    -0.10
    LY
    -0.10
    deal
    -0.10
    (Mod
    -0.10
    LK
    -0.10
     Specialty
    -0.09
    athers
    -0.09
    iones
    -0.09
     Regional
    -0.09
    POSITIVE LOGITS
     Hoy
    0.08
     Wyatt
    0.08
    oter
    0.08
    ign
    0.08
     Nev
    0.08
    quo
    0.08
     divid
    0.07
    itez
    0.07
    /groups
    0.07
     Cly
    0.07
    Activations Density 0.010%

    No Known Activations