© 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. 48665
    Prev
    Next
    INDEX
    Explanations

    section markers and copyright notices

    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
     Seymour
    -0.12
     flattering
    -0.10
     tabs
    -0.10
    /ion
    -0.10
     UNUSED
    -0.09
    /cop
    -0.09
     Orr
    -0.09
     flam
    -0.09
    _added
    -0.09
     Beit
    -0.09
    POSITIVE LOGITS
     rue
    0.08
     bout
    0.08
     Vince
    0.08
    anders
    0.08
     sho
    0.08
     dancer
    0.07
     bir
    0.07
     nad
    0.07
     Liam
    0.07
     pet
    0.07
    Activations Density 0.011%

    No Known Activations