© 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. 47426
    Prev
    Next
    INDEX
    Explanations

    body parts

    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
    stoff
    -0.11
    866
    -0.11
     Rub
    -0.10
    PET
    -0.10
    iev
    -0.10
     Patrol
    -0.10
     Gall
    -0.10
    oval
    -0.09
    oley
    -0.09
    Toast
    -0.09
    POSITIVE LOGITS
    /on
    0.12
     courtesy
    0.10
     Grove
    0.10
     cheek
    0.09
     Wen
    0.09
    SCR
    0.09
     Voy
    0.09
     tray
    0.09
     Fen
    0.08
    CRT
    0.08
    Activations Density 0.113%

    No Known Activations