© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16713
    Prev
    Next
    INDEX
    Explanations

    place names ending in ur

    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
     privat
    -0.10
    bai
    -0.09
    /reset
    -0.09
     runner
    -0.09
    chg
    -0.08
     rouge
    -0.08
     infr
    -0.08
    hest
    -0.08
     surre
    -0.08
     forgotten
    -0.08
    POSITIVE LOGITS
     deb
    0.11
    querque
    0.11
    dens
    0.11
     dudes
    0.10
    hin
    0.10
    aurus
    0.10
    cation
    0.10
    irus
    0.10
     hitch
    0.10
    adro
    0.10
    Activations Density 0.149%

    No Known Activations