© 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. 18075
    Prev
    Next
    INDEX
    Explanations

    man shooting

    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
     Kare
    -0.09
     Diy
    -0.08
    istica
    -0.08
     Sonia
    -0.08
    .obj
    -0.08
     perfection
    -0.07
     reigning
    -0.07
    /lab
    -0.07
    CACHE
    -0.07
     Hilton
    -0.07
    POSITIVE LOGITS
     stuff
    0.10
    ousy
    0.10
     Curtis
    0.10
     Parsons
    0.10
     guar
    0.10
     STDERR
    0.09
     Mess
    0.09
     altogether
    0.09
    hm
    0.09
     sez
    0.09
    Activations Density 0.054%

    No Known Activations