© 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. 33521
    Prev
    Next
    INDEX
    Explanations

    android attributes and values

    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
     macOS
    -0.10
     Safari
    -0.10
     apple
    -0.10
     Apple
    -0.10
     iPod
    -0.10
    Apple
    -0.09
     OSX
    -0.09
     APPLE
    -0.09
     iTunes
    -0.09
    Disney
    -0.08
    POSITIVE LOGITS
     Android
    0.38
     android
    0.37
    Android
    0.32
    android
    0.30
    -android
    0.27
     APK
    0.26
    (Android
    0.26
    (android
    0.25
     apk
    0.25
    .android
    0.25
    Activations Density 4.081%

    No Known Activations