© 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. 115536
    Prev
    Next
    INDEX
    Explanations

    didn't know

    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
    ally
    -0.08
    kf
    -0.08
     Af
    -0.08
     Ott
    -0.08
    alm
    -0.07
     proced
    -0.07
    alty
    -0.07
     dom
    -0.07
     hopeful
    -0.07
     “
    -0.07
    POSITIVE LOGITS
    orsch
    0.10
     rus
    0.10
    /system
    0.10
     Bold
    0.10
    _Bool
    0.10
     ...)↵
    0.10
     canonical
    0.10
     esteemed
    0.10
     Berger
    0.10
     DIR
    0.10
    Activations Density 0.049%

    No Known Activations