© 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. 3866
    Prev
    Next
    INDEX
    Explanations

    connection forming

    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
     leng
    -0.09
    raison
    -0.07
    deen
    -0.07
     col
    -0.07
    erosis
    -0.07
     -->↵↵↵
    -0.07
     SHARES
    -0.07
     practition
    -0.07
    ismo
    -0.07
     Morm
    -0.07
    POSITIVE LOGITS
     mechanism
    0.10
    asco
    0.10
    abee
    0.10
     mechanisms
    0.10
     criteria
    0.10
    peri
    0.10
    -Men
    0.09
     van
    0.09
    anders
    0.09
    _AA
    0.09
    Activations Density 0.506%

    No Known Activations