© 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. 5235
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and Russian words

    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
    нов
    -0.10
    nr
    -0.10
    aling
    -0.10
    enschaft
    -0.10
     satur
    -0.10
    bben
    -0.09
    birthdate
    -0.09
     reap
    -0.09
    ocup
    -0.09
    ë¡Ŀ
    -0.09
    POSITIVE LOGITS
     buz
    0.10
     foresee
    0.10
    IJ
    0.09
     silent
    0.09
     Vac
    0.08
     Muj
    0.08
    ¤í
    0.08
    Ī
    0.08
     dele
    0.08
    pected
    0.08
    Activations Density 0.034%

    No Known Activations