© 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. 3424
    Prev
    Next
    INDEX
    Explanations

    add, transfer, combine, pour, position

    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
     appropriately
    -0.10
     appropriate
    -0.10
    /inc
    -0.09
    observable
    -0.09
    *);↵↵
    -0.09
    iller
    -0.09
     carefully
    -0.09
     satur
    -0.08
    /root
    -0.08
     wherever
    -0.08
    POSITIVE LOGITS
    tek
    0.10
    è°
    0.09
    Collapse
    0.09
    zb
    0.08
    eya
    0.08
    Displayed
    0.08
    Ñı
    0.08
    orra
    0.08
     Collapse
    0.08
     yield
    0.08
    Activations Density 0.043%

    No Known Activations