© 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. 1948
    Prev
    Next
    INDEX
    Explanations

    Pioneer Square, Challenger, Champion, Paradigm

    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
    ule
    -0.12
    agar
    -0.11
    ий
    -0.11
    nea
    -0.10
    éĩı
    -0.10
     Flyers
    -0.10
    и
    -0.10
    age
    -0.10
    иÑħ
    -0.10
    Ĺ
    -0.10
    POSITIVE LOGITS
    ÑģÑı
    0.14
    ry
    0.13
    ries
    0.12
    imity
    0.10
    eting
    0.10
    arily
    0.09
    ong
    0.09
    ise
    0.09
    hips
    0.08
    ial
    0.08
    Activations Density 5.129%

    No Known Activations