© 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. 89611
    Prev
    Next
    INDEX
    Explanations

    978

    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
    Ĥ¹
    -0.11
     sext
    -0.10
     tad
    -0.10
    rita
    -0.10
    udes
    -0.10
    esian
    -0.10
     Carry
    -0.09
     grat
    -0.09
    ancode
    -0.09
     cand
    -0.09
    POSITIVE LOGITS
     tak
    0.10
    981
    0.09
     Fay
    0.09
     Dawson
    0.08
     Tak
    0.08
     Indie
    0.08
    atk
    0.08
    184
    0.08
     disag
    0.07
     Fault
    0.07
    Activations Density 0.008%

    No Known Activations