© 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. 27601
    Prev
    Next
    INDEX
    Explanations

    permission is hereby granted

    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
    oya
    -0.10
    .biz
    -0.09
     metic
    -0.09
     exh
    -0.09
    icate
    -0.08
    imizer
    -0.08
    ABB
    -0.08
     sat
    -0.08
    vos
    -0.08
     washed
    -0.08
    POSITIVE LOGITS
     bal
    0.10
     Mer
    0.10
     Scarborough
    0.09
     mer
    0.09
     Greenwood
    0.09
     among
    0.09
     jar
    0.09
     Erect
    0.08
     Zach
    0.08
     flashback
    0.08
    Activations Density 0.001%

    No Known Activations