© 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. 49398
    Prev
    Next
    INDEX
    Explanations

    scant, scarce, scarcely

    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
    anism
    -0.07
    ndo
    -0.07
    ÙĪد
    -0.07
    odus
    -0.07
    Ø°
    -0.07
    stadt
    -0.07
     resizable
    -0.07
    ansion
    -0.07
    IZE
    -0.06
    oron
    -0.06
    POSITIVE LOGITS
    ily
    0.19
    y
    0.18
    est
    0.16
    iest
    0.15
    iness
    0.14
    ness
    0.14
    ies
    0.13
    erness
    0.13
    uary
    0.12
    illy
    0.12
    Activations Density 0.001%

    No Known Activations