© 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. 30372
    Prev
    Next
    INDEX
    Explanations

    japanese and english mixed text

    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
    endon
    -0.10
     inters
    -0.09
    atl
    -0.08
     Worlds
    -0.08
     Meh
    -0.08
     nackt
    -0.08
     NTN
    -0.08
    oplast
    -0.08
     Dem
    -0.08
    èªŃ
    -0.08
    POSITIVE LOGITS
    íķĺëĬĶ
    0.13
    ãģĹãģ¦
    0.12
    çļĦ
    0.12
    ãģĻãĤĭ
    0.11
    ëIJĺ
    0.11
    ìĿĦ
    0.11
    ãĤĭ
    0.10
    íķĺìŬ
    0.10
    íķľ
    0.10
    ãģĦ
    0.10
    Activations Density 0.070%

    No Known Activations