© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3997
    Prev
    Next
    INDEX
    Explanations

    outcome judgement

    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
     depleted
    -0.09
     Packet
    -0.09
     interoper
    -0.09
     satur
    -0.08
     Everywhere
    -0.08
     trick
    -0.08
     projected
    -0.08
    æ²
    -0.08
     depletion
    -0.08
     terminal
    -0.08
    POSITIVE LOGITS
     favour
    0.11
     Arte
    0.11
     biases
    0.11
     fairness
    0.10
     refl
    0.10
     outcome
    0.10
     outliers
    0.10
     skew
    0.10
     pend
    0.09
     nep
    0.09
    Activations Density 0.230%

    No Known Activations