© 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. 33067
    Prev
    Next
    INDEX
    Explanations

    to work, play, visit, use, drive

    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
    arent
    -0.10
    -el
    -0.09
     exert
    -0.09
    orthy
    -0.09
    ORB
    -0.09
     rigor
    -0.09
     suspects
    -0.09
    enger
    -0.08
    vie
    -0.08
    ipe
    -0.08
    POSITIVE LOGITS
     behold
    0.20
     beh
    0.14
     Iso
    0.10
     hypoth
    0.10
     palate
    0.09
     Colum
    0.09
     messed
    0.09
     ìŀĪ
    0.09
     passages
    0.09
    hq
    0.09
    Activations Density 0.030%

    No Known Activations