© 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. 88662
    Prev
    Next
    INDEX
    Explanations

    UL followed by specific suffixes

    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
    ello
    -0.11
     gall
    -0.10
    etti
    -0.10
    lr
    -0.09
    lst
    -0.09
    geist
    -0.09
    ÑĤÑĮ
    -0.09
    Ìģ
    -0.08
    Ñİ
    -0.08
     Fro
    -0.08
    POSITIVE LOGITS
    loh
    0.11
     arity
    0.11
    kest
    0.11
    isses
    0.10
     encaps
    0.10
    ding
    0.10
    à¯įà®
    0.10
    loo
    0.10
    ders
    0.10
    engo
    0.10
    Activations Density 0.005%

    No Known Activations