© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 920
    Prev
    Next
    INDEX
    Explanations

    ending or ceasing operation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orts
    -0.09
    (&(
    -0.08
    eps
    -0.08
     expans
    -0.08
     throughout
    -0.08
    uali
    -0.08
     dub
    -0.08
    doll
    -0.08
    contro
    -0.08
     suppress
    -0.08
    POSITIVE LOGITS
     abruptly
    0.21
     abrupt
    0.16
     leaving
    0.15
     prematurely
    0.15
     gracefully
    0.14
     permanently
    0.13
    due
    0.13
     voluntarily
    0.13
     due
    0.12
    permanent
    0.12
    Activations Density 1.808%

    No Known Activations