© 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. 30507
    Prev
    Next
    INDEX
    Explanations

    in a short period

    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
     indefinitely
    -0.12
    uga
    -0.12
     perpet
    -0.12
     tanto
    -0.11
     earliest
    -0.11
    long
    -0.10
     Overs
    -0.10
    ongo
    -0.10
     plenty
    -0.10
     Ramos
    -0.10
    POSITIVE LOGITS
     span
    0.26
     quickly
    0.23
     within
    0.23
     rapid
    0.22
     overnight
    0.21
    within
    0.21
     rapidly
    0.21
     Within
    0.20
    Within
    0.20
    rapid
    0.19
    Activations Density 1.115%

    No Known Activations