© 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. 26427
    Prev
    Next
    INDEX
    Explanations

    avatar or profile picture changes

    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
     toured
    -0.10
     Colt
    -0.10
     seam
    -0.08
     meas
    -0.08
     accordion
    -0.08
     fragile
    -0.08
     nd
    -0.08
     Eng
    -0.08
     jugg
    -0.08
     measurements
    -0.07
    POSITIVE LOGITS
     avatar
    0.30
     wallpaper
    0.28
    avatar
    0.26
     wallpapers
    0.25
     Avatar
    0.24
     logo
    0.24
     profile
    0.24
     Wallpaper
    0.23
     banner
    0.21
    avatars
    0.21
    Activations Density 0.433%

    No Known Activations