© 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. 28603
    Prev
    Next
    INDEX
    Explanations

    . followed by a short string

    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
     crack
    -0.08
    bron
    -0.08
     expos
    -0.08
     dispos
    -0.08
    orden
    -0.08
     extrapol
    -0.07
    elts
    -0.07
     tritur
    -0.07
     Hoy
    -0.07
     everlasting
    -0.07
    POSITIVE LOGITS
     ($(
    0.13
     unions
    0.11
    nels
    0.10
     Hess
    0.10
     surprising
    0.10
     quirky
    0.10
    illi
    0.10
    ~↵↵
    0.10
    Thai
    0.10
    paused
    0.10
    Activations Density 0.004%

    No Known Activations