© 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. 26370
    Prev
    Next
    INDEX
    Explanations

    spoilers

    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
    uge
    -0.10
     tot
    -0.10
    antes
    -0.10
    hurst
    -0.10
    istro
    -0.10
    ingly
    -0.10
    thro
    -0.10
    ura
    -0.10
     Tot
    -0.09
    ry
    -0.09
    POSITIVE LOGITS
     spo
    0.23
     Spo
    0.21
    Spo
    0.20
     spoil
    0.20
     spoiled
    0.16
     spoilers
    0.16
     spoiler
    0.15
    spo
    0.15
     Spoon
    0.13
     spoof
    0.12
    Activations Density 0.015%

    No Known Activations