© 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. 4162
    Prev
    Next
    INDEX
    Explanations

    settings and parameters

    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¦
    -0.09
     [âĢ¦]
    -0.08
     sl
    -0.08
    âĢ¦)↵↵
    -0.07
    Ñ
    -0.07
     therein
    -0.07
    They
    -0.07
    Its
    -0.07
    .âĢ¦
    -0.07
    âĢ¦.
    -0.07
    POSITIVE LOGITS
    ï¼ĮãĢĬ
    0.13
    Collapsed
    0.12
    /goto
    0.12
    /fw
    0.12
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.12
    printStats
    0.12
     aprove
    0.12
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.11
    /cache
    0.11
     framebuffer
    0.11
    Activations Density 0.237%

    No Known Activations