© 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. 90494
    Prev
    Next
    INDEX
    Explanations

    assurance, translation, clients, byte, paradise, value, power, vaccine, evolution, economy

    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
     unl
    -0.09
    еÑģÑĤи
    -0.09
    iets
    -0.09
     underside
    -0.08
    jav
    -0.08
     Cer
    -0.08
     finer
    -0.08
    nn
    -0.08
     hij
    -0.08
    essler
    -0.08
    POSITIVE LOGITS
    (Size
    0.10
     Kush
    0.10
     {}).
    0.09
    erties
    0.09
    memset
    0.09
    353
    0.09
    uin
    0.08
    -derived
    0.08
     disap
    0.08
    /sc
    0.08
    Activations Density 0.753%

    No Known Activations