© 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. 14280
    Prev
    Next
    INDEX
    Explanations

    tracks, episodes, stories, covers

    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
    ilik
    -0.11
     Rak
    -0.11
     wield
    -0.11
     worsh
    -0.11
     suing
    -0.10
    jr
    -0.10
    -controlled
    -0.10
     Panc
    -0.10
     embr
    -0.10
     Websites
    -0.10
    POSITIVE LOGITS
     featuring
    0.19
     standalone
    0.15
     included
    0.15
     involving
    0.15
     featured
    0.15
     filmed
    0.14
     aired
    0.14
     Featuring
    0.14
     filler
    0.13
     uploaded
    0.12
    Activations Density 0.391%

    No Known Activations