© 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. 90401
    Prev
    Next
    INDEX
    Explanations

    redefined, changed, transformation

    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
    lest
    -0.10
     Kol
    -0.09
    nier
    -0.09
    {/*
    -0.08
    917
    -0.08
     Triumph
    -0.08
    acl
    -0.08
     whichever
    -0.08
     rollback
    -0.08
     whatever
    -0.08
    POSITIVE LOGITS
     altogether
    0.20
     forever
    0.17
     fundamentally
    0.15
     entirely
    0.14
     radically
    0.14
     Alto
    0.14
    alto
    0.13
     profoundly
    0.13
     paradigm
    0.13
     previously
    0.12
    Activations Density 0.231%

    No Known Activations