© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114878
    Prev
    Next
    INDEX
    Explanations

    which is or by

    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
     pony
    -0.10
    zano
    -0.09
    fg
    -0.09
    ussy
    -0.09
    ells
    -0.09
    WT
    -0.09
    ffen
    -0.09
    thal
    -0.09
     Wells
    -0.09
     Cave
    -0.09
    POSITIVE LOGITS
     Gri
    0.10
     Ashe
    0.10
    umm
    0.10
    lash
    0.09
     cen
    0.09
     rub
    0.09
     UR
    0.09
    strup
    0.09
    ethyst
    0.08
     junction
    0.08
    Activations Density 1.366%

    No Known Activations