© 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. 30811
    Prev
    Next
    INDEX
    Explanations

    Bron and its suffixes

    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
    poke
    -0.10
     poke
    -0.10
     sour
    -0.10
    aux
    -0.09
     Sour
    -0.09
    IZER
    -0.09
    ignet
    -0.09
    itat
    -0.09
    onica
    -0.09
     misunder
    -0.08
    POSITIVE LOGITS
     bron
    0.14
    Bron
    0.12
    bron
    0.12
     Bron
    0.12
    wyn
    0.11
    isl
    0.10
     Bronze
    0.10
     african
    0.10
    stein
    0.09
    agh
    0.09
    Activations Density 0.044%

    No Known Activations