© 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. 46958
    Prev
    Next
    INDEX
    Explanations

    LUNCH

    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
     Appalachian
    -0.14
     Appalach
    -0.14
     Hispanic
    -0.13
     Oklahoma
    -0.13
     Midwest
    -0.13
     Colorado
    -0.12
     Oregon
    -0.12
    Oregon
    -0.12
     Iowa
    -0.12
     Idaho
    -0.12
    POSITIVE LOGITS
     WhatsApp
    0.19
     Dubai
    0.17
     Nairobi
    0.15
     Whatsapp
    0.15
     NGO
    0.14
    WhatsApp
    0.14
     lekker
    0.14
     whatsapp
    0.14
     Bangalore
    0.13
     Tata
    0.13
    Activations Density 0.370%

    No Known Activations