© 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. 55906
    Prev
    Next
    INDEX
    Explanations

    explanatory phrases like "i.e."

    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
     cach
    -0.08
     VIA
    -0.07
     Rak
    -0.07
    Containing
    -0.07
     Stephan
    -0.07
     Spin
    -0.07
     Arc
    -0.07
     MST
    -0.06
     wo
    -0.06
    æł¼
    -0.06
    POSITIVE LOGITS
    neck
    0.11
    oley
    0.10
    ze
    0.09
     }č↵č↵č↵č↵
    0.09
     cade
    0.09
     Particularly
    0.09
    约
    0.09
    веÑĤ
    0.09
    imore
    0.09
    leness
    0.09
    Activations Density 0.078%

    No Known Activations