© 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. 1515
    Prev
    Next
    INDEX
    Explanations

    mountain, hills, country locations

    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
    ulu
    -0.10
    bearing
    -0.09
    legg
    -0.09
     Guinness
    -0.08
    ikan
    -0.08
    wares
    -0.08
    osen
    -0.08
    linger
    -0.08
    alg
    -0.08
    kees
    -0.08
    POSITIVE LOGITS
    side
    0.12
     areas
    0.11
     terrain
    0.10
    /weather
    0.10
    dw
    0.10
    å¿Ĺ
    0.10
    alling
    0.10
    /environment
    0.10
    ier
    0.10
    scape
    0.10
    Activations Density 2.228%

    No Known Activations