© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8352
    Prev
    Next
    INDEX
    Explanations

    The neuron detects and predicts conditional logic and branching in code

    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
    WA
    -0.10
     montage
    -0.10
     mover
    -0.09
     encore
    -0.09
    ebra
    -0.08
    itr
    -0.08
    ovsky
    -0.08
     зак
    -0.08
    tin
    -0.08
    /me
    -0.08
    POSITIVE LOGITS
     conditional
    0.17
     depending
    0.15
     switch
    0.15
     Conditional
    0.15
    conditional
    0.15
    switch
    0.15
    	switch
    0.14
     switches
    0.14
     tern
    0.14
    Conditional
    0.14
    Activations Density 0.758%

    No Known Activations