© 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. 29335
    Prev
    Next
    INDEX
    Explanations

    attribution or source following punctuation

    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
     testimonials
    -0.07
    ardo
    -0.06
     closely
    -0.06
    acle
    -0.06
     incom
    -0.06
    ulo
    -0.06
     Cousins
    -0.06
     interchangeable
    -0.06
     essence
    -0.06
     bare
    -0.06
    POSITIVE LOGITS
    [v
    0.17
     Follow
    0.15
    Correction
    0.15
     Source
    0.15
     Tags
    0.15
    {*
    0.15
     SOURCE
    0.15
    NOW
    0.15
    Source
    0.14
    -END
    0.14
    Activations Density 0.096%

    No Known Activations