© 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. 16213
    Prev
    Next
    INDEX
    Explanations

    case study, book, matter

    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
    -than
    -0.13
    estate
    -0.12
    fest
    -0.11
     downs
    -0.11
    alth
    -0.11
    -as
    -0.11
    -mount
    -0.11
    -time
    -0.11
     naw
    -0.11
    .rd
    -0.11
    POSITIVE LOGITS
    -esque
    0.12
    ERS
    0.08
    edly
    0.08
    ers
    0.07
    /high
    0.07
    /free
    0.07
    pers
    0.07
    patible
    0.07
    tery
    0.07
    ERY
    0.07
    Activations Density 4.431%

    No Known Activations