© 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. 6577
    Prev
    Next
    INDEX
    Explanations

    use

    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
    .LA
    -0.10
    ANI
    -0.09
    regon
    -0.09
     GURL
    -0.09
    fy
    -0.09
    InProgress
    -0.09
     Blanch
    -0.09
     pursued
    -0.09
     dikke
    -0.09
    REMOVE
    -0.09
    POSITIVE LOGITS
     use
    0.73
     usage
    0.68
     Use
    0.61
     uses
    0.60
    -use
    0.57
    Use
    0.56
    use
    0.55
    使çĶ¨
    0.53
     Usage
    0.53
     иÑģполÑĮзов
    0.50
    Activations Density 1.969%

    No Known Activations