© 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. 54601
    Prev
    Next
    INDEX
    Explanations

    Ottoman, Otto, Vittala

    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
    ey
    -0.10
    ech
    -0.10
    i
    -0.10
    pis
    -0.09
    ee
    -0.09
    ting
    -0.09
    on
    -0.09
    alog
    -0.09
    ards
    -0.09
    hood
    -0.09
    POSITIVE LOGITS
     ind
    0.09
    ï¸
    0.08
    les
    0.08
    Sin
    0.08
     Phys
    0.08
    /document
    0.08
     cod
    0.08
    ed
    0.08
    utm
    0.08
     bid
    0.08
    Activations Density 0.030%

    No Known Activations