© 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. 32866
    Prev
    Next
    INDEX
    Explanations

    INTRODUCTION, Intellij, or intubated

    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
     prudent
    -0.09
    integer
    -0.08
    Integer
    -0.08
     integer
    -0.08
    ucc
    -0.08
     owed
    -0.08
     Spr
    -0.08
    akov
    -0.07
     serialVersionUID
    -0.07
    afia
    -0.07
    POSITIVE LOGITS
    .Parse
    0.15
    .TryParse
    0.15
    angible
    0.14
    ele
    0.14
     /*<<<
    0.14
    RODUCTION
    0.14
    lectual
    0.14
    onation
    0.13
     IDEA
    0.13
    ellij
    0.13
    Activations Density 0.212%

    No Known Activations