© 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. 50315
    Prev
    Next
    INDEX
    Explanations

    online internet web

    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
    uisse
    -0.09
    Cli
    -0.09
    /dc
    -0.09
    tas
    -0.09
     pad
    -0.08
    iani
    -0.08
     gri
    -0.08
    ash
    -0.08
    -console
    -0.08
    inda
    -0.08
    POSITIVE LOGITS
     internet
    0.56
     Internet
    0.49
    internet
    0.45
    Internet
    0.43
     online
    0.39
     INTERN
    0.34
    .internet
    0.28
    online
    0.27
     Online
    0.26
     web
    0.26
    Activations Density 0.405%

    No Known Activations