© 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. 91604
    Prev
    Next
    INDEX
    Explanations

    io ending 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
    NOW
    -0.10
    udios
    -0.09
    adt
    -0.09
    icum
    -0.09
     Ziel
    -0.09
    ippy
    -0.08
    ienes
    -0.08
    imit
    -0.08
    orge
    -0.08
    crete
    -0.08
    POSITIVE LOGITS
    vascular
    0.12
    se
    0.12
    ะ
    0.11
    sek
    0.10
    /ioutil
    0.10
     Alger
    0.10
    ë¡Ŀ
    0.10
    therapy
    0.09
     wards
    0.09
    ves
    0.09
    Activations Density 0.160%

    No Known Activations