© 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. 6850
    Prev
    Next
    INDEX
    Explanations

    only followed by uncertainty or limitation

    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
     Kelley
    -0.13
     anytime
    -0.12
     kitty
    -0.12
    idis
    -0.10
     dram
    -0.10
     sidel
    -0.10
     ability
    -0.10
     anywhere
    -0.10
    nek
    -0.10
     crow
    -0.10
    POSITIVE LOGITS
     hope
    0.16
     speculate
    0.13
    hope
    0.13
     guess
    0.13
     conclude
    0.12
     assume
    0.12
     wonder
    0.12
     hoped
    0.12
     Guess
    0.11
     Hope
    0.11
    Activations Density 0.033%

    No Known Activations