© 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. 33315
    Prev
    Next
    INDEX
    Explanations

    digital technology applications

    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
     online
    -0.11
     laptops
    -0.09
     Online
    -0.09
     spam
    -0.09
     blogs
    -0.08
     Skype
    -0.08
    ãģĹãģĭ
    -0.08
     laptop
    -0.08
     Bing
    -0.08
     Blogs
    -0.08
    POSITIVE LOGITS
     Circus
    0.11
    otel
    0.11
     indeb
    0.11
     Dixon
    0.10
     prostit
    0.10
     Clipboard
    0.10
     Dough
    0.10
     Esper
    0.10
    agnostic
    0.10
     passe
    0.10
    Activations Density 1.843%

    No Known Activations