© 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. 534
    Prev
    Next
    INDEX
    Explanations

    appeal reversals and affirmations

    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
    ARED
    -0.09
     anv
    -0.08
    hint
    -0.08
     ideally
    -0.08
    prov
    -0.08
     hadn
    -0.08
     Rutgers
    -0.08
     anytime
    -0.08
    ared
    -0.08
     sue
    -0.08
    POSITIVE LOGITS
    /Dk
    0.12
     herein
    0.11
     suff
    0.10
     Suff
    0.10
     arguments
    0.10
    elden
    0.09
     canv
    0.09
     COMMENTS
    0.09
     reviewer
    0.09
    icro
    0.09
    Activations Density 0.272%

    No Known Activations