© 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. 112471
    Prev
    Next
    INDEX
    Explanations

    Top categories for content

    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
     contempl
    -0.09
     bolt
    -0.08
     Elevated
    -0.08
     Pret
    -0.08
     pret
    -0.08
     Casey
    -0.08
    .cent
    -0.08
    boss
    -0.08
    enta
    -0.08
     operative
    -0.08
    POSITIVE LOGITS
    .ContextCompat
    0.11
    acas
    0.10
    ordion
    0.09
    abl
    0.09
     uncon
    0.09
    aceous
    0.09
    ìĭĿ
    0.09
     Belarus
    0.09
    ìĭł
    0.08
    ollen
    0.08
    Activations Density 0.171%

    No Known Activations