© 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. 89468
    Prev
    Next
    INDEX
    Explanations

    Pistacia, pistons, Mindanao

    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
    itel
    -0.09
    rush
    -0.09
     Optionally
    -0.09
     Mant
    -0.08
     dense
    -0.08
    inite
    -0.08
    è¡
    -0.08
     Sugar
    -0.08
    utable
    -0.08
     inherited
    -0.08
    POSITIVE LOGITS
    ä
    0.10
     reserve
    0.10
    kir
    0.09
     pitching
    0.09
    vez
    0.09
    jem
    0.09
    reed
    0.09
    rawn
    0.08
    disposing
    0.08
    lag
    0.08
    Activations Density 0.001%

    No Known Activations