© 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. 114447
    Prev
    Next
    INDEX
    Explanations

    jak & jakarta

    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
    mps
    -0.12
    ony
    -0.10
    akin
    -0.10
    tps
    -0.09
     squirt
    -0.09
    ftware
    -0.09
    ELL
    -0.09
     gy
    -0.09
    ONY
    -0.09
     Fol
    -0.09
    POSITIVE LOGITS
    zure
    0.10
     ~~
    0.10
     alike
    0.09
     conspic
    0.09
    /pro
    0.09
    chai
    0.08
     Came
    0.08
     Watson
    0.08
     Rising
    0.08
     conspicuous
    0.08
    Activations Density 0.001%

    No Known Activations