© 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. 56103
    Prev
    Next
    INDEX
    Explanations

    patients with

    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
    ultipart
    -0.10
     tamp
    -0.09
    ulet
    -0.09
    leton
    -0.09
    inton
    -0.08
     selves
    -0.08
    .gray
    -0.08
    éł
    -0.08
    دÙĬ
    -0.08
    ided
    -0.08
    POSITIVE LOGITS
     barg
    0.08
     trans
    0.08
     Virt
    0.08
     nuis
    0.08
     simultaneously
    0.07
     Masc
    0.07
    -any
    0.07
     cyc
    0.07
    CK
    0.07
    iq
    0.07
    Activations Density 0.065%

    No Known Activations