© 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. 49366
    Prev
    Next
    INDEX
    Explanations

    younger relative

    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
    isi
    -0.10
    ento
    -0.10
     Perkins
    -0.10
    ecom
    -0.09
     uncon
    -0.09
    flows
    -0.09
     cavern
    -0.09
     ports
    -0.09
    дÑĢ
    -0.09
     Tango
    -0.09
    POSITIVE LOGITS
     (<
    0.20
    blood
    0.17
    (er
    0.17
    -aged
    0.17
    -generation
    0.16
     age
    0.16
    sters
    0.15
    -age
    0.15
     ages
    0.14
     generation
    0.13
    Activations Density 0.031%

    No Known Activations