© 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. 112362
    Prev
    Next
    INDEX
    Explanations

    master clock, player, quality, cylinder

    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
    nel
    -0.12
    noch
    -0.10
     cá
    -0.09
    res
    -0.09
    endar
    -0.09
    ality
    -0.08
    ths
    -0.08
    vt
    -0.08
    ноÑģÑĤи
    -0.08
    ulta
    -0.08
    POSITIVE LOGITS
    mind
    0.24
    pieces
    0.20
    stroke
    0.16
    piece
    0.16
    bate
    0.16
    fully
    0.14
    /sl
    0.14
    arbeit
    0.13
    -sl
    0.12
    ful
    0.12
    Activations Density 0.096%

    No Known Activations