© 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. 7632
    Prev
    Next
    INDEX
    Explanations

    German names and places

    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
     ganze
    -0.17
     bisher
    -0.17
     jede
    -0.17
     erfolgre
    -0.17
     aktuellen
    -0.17
     entsprech
    -0.16
     allerdings
    -0.16
     irgend
    -0.16
     zwar
    -0.16
     jedem
    -0.16
    POSITIVE LOGITS
     Germany
    0.26
     German
    0.24
    Germany
    0.23
     GmbH
    0.22
     Germans
    0.22
    German
    0.21
     von
    0.19
     germany
    0.19
     Friedrich
    0.18
     Deutsche
    0.18
    Activations Density 1.367%

    No Known Activations