© 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. 2959
    Prev
    Next
    INDEX
    Explanations

    effect or action

    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
    pin
    -0.09
     carrying
    -0.09
     readily
    -0.08
    egg
    -0.08
    PIN
    -0.08
     associ
    -0.08
    ivan
    -0.08
     escalating
    -0.08
     spatial
    -0.08
    ola
    -0.08
    POSITIVE LOGITS
     effects
    0.12
    -effect
    0.10
     effect
    0.10
     Mechan
    0.10
     Effects
    0.10
     indirect
    0.09
     Benef
    0.09
     EFFECT
    0.09
     mechanism
    0.09
     offsets
    0.08
    Activations Density 0.367%

    No Known Activations