© 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. 6545
    Prev
    Next
    INDEX
    Explanations

    difference between success or failure

    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
     somew
    -0.09
    mere
    -0.08
     fres
    -0.08
     genuine
    -0.08
     beste
    -0.08
     zar
    -0.07
    mach
    -0.07
     Ih
    -0.07
     Springs
    -0.07
    acer
    -0.07
    POSITIVE LOGITS
    —not
    0.13
     ultimately
    0.13
    -not
    0.12
    ongoose
    0.11
    licht
    0.11
    eking
    0.11
     FIRST
    0.11
     initially
    0.11
     first
    0.10
    esch
    0.10
    Activations Density 0.187%

    No Known Activations