© 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. 4122
    Prev
    Next
    INDEX
    Explanations

    date and time stamps

    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
     silent
    -0.08
     borough
    -0.08
     Friedman
    -0.08
     dangling
    -0.07
    prs
    -0.07
     Cald
    -0.07
     Vance
    -0.07
    ansi
    -0.07
     tri
    -0.07
     Tri
    -0.07
    POSITIVE LOGITS
     Doyle
    0.11
    alin
    0.10
    kre
    0.10
    :+
    0.10
    ál
    0.10
    apel
    0.10
     Bounds
    0.09
    soles
    0.09
    estre
    0.09
     âĺĨ
    0.09
    Activations Density 0.139%

    No Known Activations