© 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. 3137
    Prev
    Next
    INDEX
    Explanations

    programming constructs like else, return, break

    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
    dur
    -0.09
     lose
    -0.08
     Unless
    -0.08
    lam
    -0.08
    DataProvider
    -0.08
    urgeon
    -0.08
    antan
    -0.07
     resta
    -0.07
     Bars
    -0.07
    ObjectType
    -0.07
    POSITIVE LOGITS
    gu
    0.10
     em
    0.10
     lev
    0.10
     hypo
    0.09
     Empty
    0.09
     instal
    0.09
    gie
    0.09
    BREAK
    0.09
    bit
    0.08
     absence
    0.08
    Activations Density 0.064%

    No Known Activations