© 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. 54446
    Prev
    Next
    INDEX
    Explanations

    class inheritance and generic constraints

    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
    ikan
    -0.09
    ORTH
    -0.08
    ldr
    -0.08
     Sle
    -0.08
    azz
    -0.08
    haps
    -0.08
    (++
    -0.08
    eter
    -0.08
    ation
    -0.07
    XYZ
    -0.07
    POSITIVE LOGITS
     "-";↵
    0.10
     pret
    0.09
    ango
    0.09
    ÙĬÙĦ
    0.09
    queda
    0.09
     caps
    0.08
    ry
    0.08
    ugg
    0.08
    unami
    0.08
    pret
    0.08
    Activations Density 0.007%

    No Known Activations