© 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. 115662
    Prev
    Next
    INDEX
    Explanations

    all followed by positive or negative outcomes

    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
    enic
    -0.10
    /il
    -0.10
    och
    -0.10
    oop
    -0.09
    678
    -0.09
    olg
    -0.09
     Alg
    -0.09
    uada
    -0.09
     dang
    -0.09
    -stars
    -0.09
    POSITIVE LOGITS
    ayed
    0.11
     unknow
    0.10
     along
    0.09
     uncon
    0.09
     Erick
    0.09
     Planning
    0.09
    adding
    0.08
     involuntary
    0.08
     Killer
    0.08
     UD
    0.08
    Activations Density 0.075%

    No Known Activations