© 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. 28186
    Prev
    Next
    INDEX
    Explanations

    jacquesm, tomohawk, kirstendirksen, cpac, mquaes, pulisse, recoiledsnake, ilamont, edu, fancy

    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
     vX
    -0.10
    izza
    -0.10
    åºĹ
    -0.10
    .quest
    -0.10
     crunch
    -0.09
    SJ
    -0.09
     Cheat
    -0.09
     mies
    -0.09
     monet
    -0.09
    ienes
    -0.09
    POSITIVE LOGITS
     Pou
    0.11
    aan
    0.10
     crossword
    0.09
    -overlay
    0.09
     proved
    0.09
     prof
    0.08
     Hancock
    0.08
     panorama
    0.08
     pockets
    0.08
     spo
    0.08
    Activations Density 0.221%

    No Known Activations