© 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. 28054
    Prev
    Next
    INDEX
    Explanations

    boost and body tags

    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
    [âĢ¦
    -0.11
    âĢ¦↵↵↵↵
    -0.10
    umi
    -0.08
     derp
    -0.08
    -0.08
    -0.08
     —
    -0.08
     âĢİ
    -0.08
     curated
    -0.07
     COVID
    -0.07
    POSITIVE LOGITS
     didnt
    0.13
    anel
    0.12
     Said
    0.12
     Ive
    0.11
     cum
    0.11
     posto
    0.11
     Tub
    0.10
    agu
    0.10
    cmp
    0.10
     punct
    0.10
    Activations Density 0.041%

    No Known Activations