© 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. 1317
    Prev
    Next
    INDEX
    Explanations

    numbers followed by period or comma

    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
    ly
    -0.11
    ingly
    -0.09
    dy
    -0.09
    ney
    -0.09
    FER
    -0.09
    ing
    -0.09
    rd
    -0.09
    ivities
    -0.09
    imately
    -0.09
    tee
    -0.08
    POSITIVE LOGITS
    ality
    0.14
    ÃĦ
    0.11
    <<<
    0.10
    ERGY
    0.10
    æŀľ
    0.10
    <<<<
    0.10
    а
    0.10
    nds
    0.10
    al
    0.10
    aten
    0.10
    Activations Density 3.504%

    No Known Activations