© 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. 113360
    Prev
    Next
    INDEX
    Explanations

    numbers 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
     pant
    -0.10
    fal
    -0.09
    ensch
    -0.09
     pens
    -0.08
    áŁĴáŀ
    -0.08
    [__
    -0.08
     [_
    -0.08
     backs
    -0.08
     Brothers
    -0.08
     Termin
    -0.08
    POSITIVE LOGITS
     chr
    0.11
     billions
    0.11
     millions
    0.10
     senior
    0.10
     shr
    0.10
     Senior
    0.10
    idis
    0.10
    laden
    0.10
    ISON
    0.10
     Millions
    0.10
    Activations Density 0.013%

    No Known Activations