© 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. 163
    Prev
    Next
    INDEX
    Explanations

    201_

    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
    اÙģ
    -0.08
    hei
    -0.08
    enta
    -0.08
    acks
    -0.06
     inf
    -0.06
    Ĺı
    -0.06
     rigid
    -0.06
    pering
    -0.06
    198
    -0.06
     Fuse
    -0.06
    POSITIVE LOGITS
    -www
    0.12
     initComponents
    0.11
    irie
    0.11
    esis
    0.10
     unas
    0.10
    st
    0.10
    ampil
    0.10
    	Il
    0.10
    _CREATED
    0.10
    hire
    0.10
    Activations Density 0.410%

    No Known Activations