© 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. 3838
    Prev
    Next
    INDEX
    Explanations

    dr, DR, dru, Dron, Driv, Druid

    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
     break
    -0.09
     outright
    -0.09
     bump
    -0.08
    amber
    -0.08
     prop
    -0.08
     critical
    -0.08
    rais
    -0.08
    atti
    -0.08
    atsu
    -0.07
    uche
    -0.07
    POSITIVE LOGITS
     Manhattan
    0.14
    astically
    0.13
    aper
    0.13
    AGON
    0.12
    ekyll
    0.12
    ystone
    0.11
    IFT
    0.11
    iven
    0.11
    uida
    0.11
    agoon
    0.11
    Activations Density 0.171%

    No Known Activations