© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 27043
    Prev
    Next
    INDEX
    Explanations

    conjunction 'and' followed by 'of'

    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
    ewater
    -0.10
     даннÑĭ
    -0.10
    ks
    -0.10
    ksam
    -0.10
    atu
    -0.09
     Geb
    -0.09
    FTA
    -0.09
    —and
    -0.09
    xs
    -0.08
     ns
    -0.08
    POSITIVE LOGITS
     of
    0.27
     cá»§a
    0.15
    of
    0.14
     ÑģпиÑģка
    0.14
    _of
    0.13
    (of
    0.12
    [of
    0.12
    	of
    0.11
     Of
    0.11
    Of
    0.10
    Activations Density 0.759%

    No Known Activations