© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31862
    Prev
    Next
    INDEX
    Explanations

    can translate

    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
     languages
    -0.11
     culturally
    -0.11
     amb
    -0.11
     Languages
    -0.10
    Languages
    -0.10
    isko
    -0.09
    arsi
    -0.09
     typo
    -0.09
     readings
    -0.09
     reading
    -0.09
    POSITIVE LOGITS
     UNIVERS
    0.12
     universal
    0.12
     resort
    0.12
     guesses
    0.11
     Resort
    0.11
     reliance
    0.11
     universally
    0.11
     mutual
    0.11
     resorts
    0.11
     fortunately
    0.11
    Activations Density 0.101%

    No Known Activations