© 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. 30855
    Prev
    Next
    INDEX
    Explanations

    original

    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
     scr
    -0.07
     descriptive
    -0.07
     glamour
    -0.07
    spa
    -0.07
     Pert
    -0.07
     Renaissance
    -0.06
     knight
    -0.06
    adan
    -0.06
    cke
    -0.06
    auer
    -0.06
    POSITIVE LOGITS
     Soc
    0.13
    dzi
    0.11
    dle
    0.11
     Nu
    0.11
     unto
    0.10
     ):↵↵
    0.10
     dispose
    0.10
     Wis
    0.10
     sanction
    0.10
    subcategory
    0.10
    Activations Density 0.001%

    No Known Activations