© 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. 56411
    Prev
    Next
    INDEX
    Explanations

    adenomas

    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
    PLAIN
    -0.10
    eve
    -0.09
    par
    -0.09
    fm
    -0.09
    Ster
    -0.09
    argin
    -0.09
    ofday
    -0.09
     Lub
    -0.08
     locating
    -0.08
    lobals
    -0.08
    POSITIVE LOGITS
     Gabri
    0.08
     stepping
    0.08
    olo
    0.08
     pyl
    0.08
    stone
    0.07
    abe
    0.07
    amm
    0.07
     Analyzer
    0.07
     pleasure
    0.07
    kul
    0.07
    Activations Density 0.056%

    No Known Activations