© 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. 27335
    Prev
    Next
    INDEX
    Explanations

    multiples of quantity

    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
     Fot
    -0.10
    apas
    -0.10
    elp
    -0.10
     BEST
    -0.10
    ensen
    -0.09
    urr
    -0.09
    Ù¾
    -0.09
    gren
    -0.09
     interiors
    -0.09
     specifics
    -0.09
    POSITIVE LOGITS
     amount
    0.15
     number
    0.14
     usual
    0.14
     normal
    0.12
     horsepower
    0.10
     distance
    0.10
     size
    0.10
     length
    0.09
    ormal
    0.09
     Normal
    0.09
    Activations Density 0.027%

    No Known Activations