© 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. 3332
    Prev
    Next
    INDEX
    Explanations

    Objective-C method declarations

    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
    erve
    -0.08
     elevation
    -0.08
    ibel
    -0.08
     convict
    -0.08
     elev
    -0.08
    agg
    -0.07
    دÙĩ
    -0.07
     spo
    -0.07
     sp
    -0.07
     Bull
    -0.07
    POSITIVE LOGITS
    .mit
    0.11
    quee
    0.10
     shrink
    0.09
    antas
    0.09
    naz
    0.09
    agna
    0.09
    aira
    0.09
    /utility
    0.09
     urgently
    0.09
    atters
    0.08
    Activations Density 0.037%

    No Known Activations