© 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. 5057
    Prev
    Next
    INDEX
    Explanations

    Russian punctuation and conjunctions

    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
    atura
    -0.10
    esk
    -0.10
    dee
    -0.10
    pek
    -0.10
     groom
    -0.09
     str
    -0.09
    atore
    -0.09
    ï¼Īç¬ij
    -0.09
    yas
    -0.09
    hed
    -0.09
    POSITIVE LOGITS
    aneously
    0.11
     onwards
    0.11
    modo
    0.10
     contrario
    0.10
    же
    0.10
    etheless
    0.10
    edly
    0.09
    ि
    0.09
    íķĺìŬ
    0.09
     Zwe
    0.09
    Activations Density 0.316%

    No Known Activations