© 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. 88630
    Prev
    Next
    INDEX
    Explanations

    linguistic features and semantics

    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
     translated
    -0.12
    translated
    -0.10
    elib
    -0.10
     RAW
    -0.10
     flows
    -0.10
     Kov
    -0.10
     translate
    -0.10
     Excell
    -0.10
     Spiel
    -0.10
     annunci
    -0.09
    POSITIVE LOGITS
     Lingu
    0.28
     lingu
    0.28
     linguistic
    0.26
     lexical
    0.26
    lexical
    0.23
     deix
    0.21
     Corpus
    0.20
     phon
    0.19
     synt
    0.19
     speakers
    0.19
    Activations Density 2.072%

    No Known Activations