© 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. 117186
    Prev
    Next
    INDEX
    Explanations

    prime factors, common denominator, or derivative

    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
     hal
    -0.11
     mute
    -0.10
     Poz
    -0.10
     row
    -0.10
     unfore
    -0.10
     ladies
    -0.10
     Ski
    -0.10
     rule
    -0.10
    fh
    -0.10
    dex
    -0.10
    POSITIVE LOGITS
    alian
    0.08
    ering
    0.08
     Garrett
    0.08
     Bend
    0.08
    urch
    0.07
    icast
    0.07
     prostitute
    0.07
    atura
    0.07
    istik
    0.07
     vend
    0.07
    Activations Density 0.001%

    No Known Activations