© 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. 50567
    Prev
    Next
    INDEX
    Explanations

    an [language type]

    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
     unmarried
    -0.10
     Zak
    -0.10
    achs
    -0.10
     Ve
    -0.09
     corre
    -0.09
    Łèĥ½
    -0.09
     multim
    -0.09
     Quint
    -0.09
    andre
    -0.09
     personality
    -0.09
    POSITIVE LOGITS
     languages
    0.44
     language
    0.36
     Languages
    0.32
     dialect
    0.29
    languages
    0.28
    Languages
    0.28
     spoken
    0.28
     langue
    0.27
    language
    0.27
     Language
    0.26
    Activations Density 0.702%

    No Known Activations