© 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. 56524
    Prev
    Next
    INDEX
    Explanations

    metastases

    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
    orm
    -0.08
    amer
    -0.07
    emi
    -0.06
     shove
    -0.06
    emes
    -0.06
    acity
    -0.06
     territorial
    -0.06
    ìłĦ
    -0.06
    -hidden
    -0.06
    éļIJèĹı
    -0.06
    POSITIVE LOGITS
    iasi
    0.11
    (es
    0.11
    uez
    0.11
    /null
    0.10
    allo
    0.10
    [s
    0.10
    itet
    0.10
     Kane
    0.10
    IRECTION
    0.10
    inscription
    0.10
    Activations Density 0.005%

    No Known Activations