© 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. 17740
    Prev
    Next
    INDEX
    Explanations

    java or android imports

    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
    	S
    -0.14
    .JTable
    -0.12
    .JScrollPane
    -0.12
     sour
    -0.11
    \S
    -0.11
     Stadium
    -0.11
    -St
    -0.11
    .St
    -0.11
    stell
    -0.11
    *S
    -0.11
    POSITIVE LOGITS
     U
    0.12
     Union
    0.11
     Umb
    0.11
     United
    0.11
     u
    0.10
     Uniform
    0.10
     Var
    0.10
     Unified
    0.10
     uom
    0.10
    U
    0.10
    Activations Density 0.070%

    No Known Activations