© 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. 31578
    Prev
    Next
    INDEX
    Explanations

    physiology of

    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
     impro
    -0.08
     assignable
    -0.08
     ded
    -0.08
     inf
    -0.08
     truth
    -0.08
    immel
    -0.07
     fancy
    -0.07
    alive
    -0.07
    Rand
    -0.07
     er
    -0.07
    POSITIVE LOGITS
    ieres
    0.12
    exas
    0.10
     “âĢ¦
    0.10
    eto
    0.10
     Leer
    0.10
     Dah
    0.10
    -git
    0.10
    adr
    0.10
     pricing
    0.10
    uj
    0.10
    Activations Density 0.001%

    No Known Activations