© 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. 91038
    Prev
    Next
    INDEX
    Explanations

    LangVersion or TargetFramework

    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
    GRP
    -0.10
    nip
    -0.10
    noch
    -0.10
    lero
    -0.09
    iert
    -0.09
    dna
    -0.09
    iken
    -0.09
     budgets
    -0.09
    ftar
    -0.09
    uni
    -0.09
    POSITIVE LOGITS
    <thead
    0.09
     Charm
    0.08
     SAL
    0.08
    京
    0.08
     Sal
    0.08
     arousal
    0.08
     sal
    0.08
    <td
    0.07
    eneg
    0.07
     Dun
    0.07
    Activations Density 2.297%

    No Known Activations