© 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. 33188
    Prev
    Next
    INDEX
    Explanations

    Foreign languages and special characters

    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
     Wir
    -0.09
    amel
    -0.09
     Arnold
    -0.09
    rab
    -0.09
    anden
    -0.09
    uze
    -0.08
    LR
    -0.08
    ully
    -0.08
    emos
    -0.08
    ecc
    -0.08
    POSITIVE LOGITS
     hai
    0.13
     intermitt
    0.11
    ãģĤãĤĬ
    0.10
     sein
    0.10
    abe
    0.10
    elpers
    0.10
    inta
    0.10
    ä
    0.10
     ìŀĪëĭ¤
    0.10
     ìŀĪ
    0.10
    Activations Density 0.011%

    No Known Activations