© 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. 92133
    Prev
    Next
    INDEX
    Explanations

    alternative to traditional/conventional

    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
     Hess
    -0.10
    igli
    -0.10
     Dirt
    -0.09
     libr
    -0.09
     Crusher
    -0.09
    igner
    -0.08
    uil
    -0.08
    Arthur
    -0.08
     pw
    -0.08
     Arthur
    -0.08
    POSITIVE LOGITS
     expensive
    0.27
     costly
    0.25
     invasive
    0.22
     surgery
    0.22
     pricey
    0.21
     pharmaceutical
    0.19
     resort
    0.19
     Surgery
    0.18
     surgical
    0.17
     chemicals
    0.17
    Activations Density 0.391%

    No Known Activations