© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 47505
    Prev
    Next
    INDEX
    Explanations

    manufacturing related terms

    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
    utra
    -0.10
    adro
    -0.10
     sexist
    -0.09
     ovar
    -0.09
     Shipping
    -0.09
     ())
    -0.09
     Bul
    -0.09
     tav
    -0.09
    PIO
    -0.09
     bele
    -0.09
    POSITIVE LOGITS
     Gesch
    0.10
    ê¸Ģ
    0.09
     Baldwin
    0.08
     facult
    0.08
     FORWARD
    0.08
    _rec
    0.08
     Gaines
    0.08
     Gra
    0.08
     recurs
    0.08
     fantasies
    0.08
    Activations Density 0.001%

    No Known Activations