© 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. 27057
    Prev
    Next
    INDEX
    Explanations

    sharing comments, opinions, or stories

    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
     unreal
    -0.10
     bog
    -0.09
    lug
    -0.09
     Bog
    -0.09
     Arn
    -0.08
    udo
    -0.08
     dreamed
    -0.08
    iez
    -0.08
    aille
    -0.08
     swamp
    -0.08
    POSITIVE LOGITS
     Deg
    0.11
    Deg
    0.10
     below
    0.10
    _story
    0.10
    Dash
    0.09
     Rocks
    0.09
    onga
    0.09
     storyboard
    0.09
    Goods
    0.09
     Compilation
    0.09
    Activations Density 0.021%

    No Known Activations