© 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. 1235
    Prev
    Next
    INDEX
    Explanations

    multiple, difficulty, increased, positive, completion, bullet

    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
    urv
    -0.08
    React
    -0.08
     squarely
    -0.08
     Severity
    -0.08
     ={↵
    -0.08
     originals
    -0.08
     gir
    -0.08
    Fx
    -0.08
     frail
    -0.08
     Deprecated
    -0.08
    POSITIVE LOGITS
     etc
    0.16
     lack
    0.11
     increased
    0.11
    etc
    0.11
     followed
    0.11
     occasional
    0.10
    /or
    0.10
     avoidance
    0.10
     various
    0.10
     ....↵↵
    0.10
    Activations Density 1.965%

    No Known Activations