© 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. 48390
    Prev
    Next
    INDEX
    Explanations

    want when you need it

    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
    arna
    -0.13
    ées
    -0.12
    iev
    -0.12
    zia
    -0.11
     Julio
    -0.11
     Reed
    -0.11
    uali
    -0.11
    OUCH
    -0.11
    eus
    -0.11
     Lafayette
    -0.11
    POSITIVE LOGITS
    /by
    0.10
    ,
    0.09
     sooner
    0.09
     QUICK
    0.09
     very
    0.09
     faster
    0.08
     fast
    0.08
     quickly
    0.08
    ets
    0.08
    /location
    0.08
    Activations Density 0.812%

    No Known Activations