© 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. 46475
    Prev
    Next
    INDEX
    Explanations

    moth

    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
    iolet
    -0.09
     vis
    -0.09
    phan
    -0.09
     gentleman
    -0.08
    itted
    -0.08
     Rav
    -0.08
    ugins
    -0.08
     Washer
    -0.08
     illum
    -0.08
    rag
    -0.07
    POSITIVE LOGITS
    heck
    0.11
     Carlo
    0.09
    hi
    0.09
     tastes
    0.09
     mastur
    0.09
     toler
    0.09
     spokeswoman
    0.09
     paradox
    0.09
    lie
    0.09
     nutrit
    0.09
    Activations Density 0.002%

    No Known Activations