© 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. 17412
    Prev
    Next
    INDEX
    Explanations

    numbers followed by percent, rd, th, or /

    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
     Ank
    -0.08
    onus
    -0.08
    ahan
    -0.08
     subsidi
    -0.08
    cased
    -0.08
     BH
    -0.07
     primitives
    -0.07
    loads
    -0.07
    ativ
    -0.07
     negate
    -0.07
    POSITIVE LOGITS
    âĢ²
    0.24
    âĢ³
    0.23
    ths
    0.18
    th
    0.17
    'er
    0.17
    ½
    0.17
    ï¸ı
    0.16
    º
    0.16
    s
    0.16
    -ing
    0.15
    Activations Density 0.286%

    No Known Activations