© 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. 112398
    Prev
    Next
    INDEX
    Explanations

    language and communication methods

    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
    udas
    -0.10
    enet
    -0.08
    loys
    -0.08
    hurst
    -0.08
    vik
    -0.08
     reput
    -0.08
     hare
    -0.08
    asca
    -0.07
     dyn
    -0.07
     canned
    -0.07
    POSITIVE LOGITS
     language
    0.35
     speak
    0.31
     languages
    0.29
    language
    0.29
     Language
    0.27
     fluent
    0.27
     Speak
    0.27
     speaks
    0.27
     translate
    0.26
     translating
    0.25
    Activations Density 0.185%

    No Known Activations