© 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. 49800
    Prev
    Next
    INDEX
    Explanations

    German place names and compound words

    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
    Doc
    -0.10
    ocha
    -0.09
     uncon
    -0.09
     bona
    -0.09
     Hoff
    -0.09
     Docs
    -0.09
    docs
    -0.09
    mind
    -0.09
    grand
    -0.09
     hon
    -0.09
    POSITIVE LOGITS
    @stop
    0.09
     Atlas
    0.09
     montage
    0.09
    FORMANCE
    0.09
    à§į
    0.09
    /theme
    0.09
     Pompe
    0.09
     encodeURIComponent
    0.09
    andelier
    0.09
    -less
    0.09
    Activations Density 0.104%

    No Known Activations