© 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. 112635
    Prev
    Next
    INDEX
    Explanations

    Names followed by comma or title

    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
     mighty
    -0.10
    izzle
    -0.09
     decrement
    -0.08
     super
    -0.08
     contestant
    -0.08
     bo
    -0.08
     unf
    -0.08
     superstar
    -0.08
     Morales
    -0.08
     lovely
    -0.08
    POSITIVE LOGITS
    nze
    0.10
    yon
    0.10
     Vick
    0.09
    koa
    0.09
    chor
    0.09
    ufe
    0.09
    anga
    0.09
    getting
    0.09
     retiring
    0.09
    iken
    0.09
    Activations Density 0.706%

    No Known Activations