© 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. 29392
    Prev
    Next
    INDEX
    Explanations

    DillonArmstrongrank

    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
     Fol
    -0.11
     Pent
    -0.11
     evidently
    -0.11
    iard
    -0.11
     Investigation
    -0.11
     Universal
    -0.10
     deton
    -0.10
     -:
    -0.10
     Lak
    -0.10
    zl
    -0.10
    POSITIVE LOGITS
    atur
    0.09
     Howell
    0.09
     Zot
    0.08
     Tow
    0.08
     cin
    0.07
     Baron
    0.07
    ð
    0.07
     Paula
    0.07
     \č↵
    0.07
     chan
    0.07
    Activations Density 0.001%

    No Known Activations