© 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. 56373
    Prev
    Next
    INDEX
    Explanations

    ingredients and dishes

    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
    emm
    -0.10
     readily
    -0.10
    adol
    -0.10
    Gro
    -0.09
     Basic
    -0.09
    pa
    -0.09
     Bilder
    -0.09
    ç©
    -0.09
     Lifetime
    -0.09
    HIR
    -0.09
    POSITIVE LOGITS
    uckle
    0.08
    lein
    0.08
     scav
    0.08
    felt
    0.08
    interrupt
    0.07
     drone
    0.07
     pri
    0.07
     Nim
    0.07
     Ain
    0.07
    .mit
    0.07
    Activations Density 0.022%

    No Known Activations