© 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. 58067
    Prev
    Next
    INDEX
    Explanations

    tension, tensions, tensioning, tension-resisting

    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
    inka
    -0.12
    fmt
    -0.11
     mascara
    -0.10
    emma
    -0.10
    esh
    -0.10
    ppo
    -0.10
    ORY
    -0.10
     Ment
    -0.09
    jo
    -0.09
    ister
    -0.09
    POSITIVE LOGITS
     tensions
    0.10
    dre
    0.10
     tension
    0.10
    ened
    0.08
    ly
    0.08
    -Ta
    0.08
    ención
    0.08
     wire
    0.08
    ed
    0.08
    ire
    0.08
    Activations Density 0.006%

    No Known Activations