© 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. 18050
    Prev
    Next
    INDEX
    Explanations

    watching television or videos

    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
     fian
    -0.11
     reserv
    -0.09
     Mods
    -0.09
     Bund
    -0.09
     screenshot
    -0.09
     hearing
    -0.09
    289
    -0.09
    ny
    -0.09
     groin
    -0.09
    136
    -0.09
    POSITIVE LOGITS
     television
    0.18
     TV
    0.16
     tv
    0.14
     televis
    0.13
     televised
    0.12
    tv
    0.12
     Weaver
    0.11
     UNIT
    0.10
    TV
    0.10
    Tv
    0.10
    Activations Density 0.024%

    No Known Activations