© 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. 18194
    Prev
    Next
    INDEX
    Explanations

    Empire of

    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
    çİĩ
    -0.09
     padd
    -0.08
     complement
    -0.08
     gad
    -0.08
    iant
    -0.08
    idad
    -0.07
    ime
    -0.07
     emptied
    -0.07
     worst
    -0.07
     surre
    -0.07
    POSITIVE LOGITS
    -wide
    0.18
    wide
    0.15
    -building
    0.14
    -builder
    0.13
     Builders
    0.12
    /Common
    0.12
    eer
    0.12
    Wide
    0.12
     Strikes
    0.11
    stag
    0.11
    Activations Density 0.055%

    No Known Activations