© 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. 31726
    Prev
    Next
    INDEX
    Explanations

    Apple Inc

    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
    nh
    -0.09
     Trident
    -0.09
    ndo
    -0.08
    åĭ
    -0.08
    est
    -0.08
    edly
    -0.08
    epad
    -0.08
    rts
    -0.08
    nah
    -0.08
    semb
    -0.08
    POSITIVE LOGITS
     cider
    0.24
    auce
    0.18
    /apple
    0.18
    bee
    0.17
    baum
    0.16
    WebKit
    0.16
     pie
    0.15
     Pie
    0.15
    seed
    0.15
    ause
    0.14
    Activations Density 0.095%

    No Known Activations