© 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. 49229
    Prev
    Next
    INDEX
    Explanations

    He said

    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
     acknow
    -0.12
     nack
    -0.12
     wearer
    -0.12
    /arm
    -0.11
     belts
    -0.11
    uar
    -0.11
     disarm
    -0.11
    ACHI
    -0.11
     Shoulder
    -0.11
    achi
    -0.11
    POSITIVE LOGITS
     Aure
    0.09
    uro
    0.09
    aine
    0.08
     directed
    0.08
     aiming
    0.08
     feed
    0.07
     aimed
    0.07
     sewage
    0.07
     Sco
    0.07
     swings
    0.07
    Activations Density 0.005%

    No Known Activations