© 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. 113443
    Prev
    Next
    INDEX
    Explanations

    software and associated documentation files

    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
     compartments
    -0.10
     Nich
    -0.10
    /pm
    -0.10
    ¥
    -0.10
     Ajax
    -0.10
    672
    -0.10
     Cyr
    -0.09
    agr
    -0.09
    deadline
    -0.09
    CEF
    -0.09
    POSITIVE LOGITS
    kl
    0.10
     capital
    0.09
    rawl
    0.09
    esc
    0.09
     KL
    0.08
    ONO
    0.08
     cons
    0.08
     Shield
    0.08
     class
    0.08
     Highland
    0.08
    Activations Density 0.002%

    No Known Activations