© 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. 33801
    Prev
    Next
    INDEX
    Explanations

    language, dialect, and speech variations

    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
     Maison
    -0.10
     Spl
    -0.10
    bac
    -0.10
     Lic
    -0.10
    Unhandled
    -0.09
     Matte
    -0.09
     brute
    -0.09
     Nacht
    -0.09
     stor
    -0.09
     Kos
    -0.09
    POSITIVE LOGITS
     slang
    0.38
     dialect
    0.36
     collo
    0.34
     vern
    0.32
     speech
    0.27
     language
    0.27
     speak
    0.25
     spoken
    0.24
     accent
    0.23
     Vern
    0.23
    Activations Density 0.232%

    No Known Activations