© 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. 1664
    Prev
    Next
    INDEX
    Explanations

    speed and quickness

    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
    _extend
    -0.10
    hy
    -0.10
    cro
    -0.10
    -helper
    -0.10
    ingen
    -0.09
     slowly
    -0.09
    hip
    -0.09
     contro
    -0.09
    羣
    -0.09
    éĻĨ
    -0.09
    POSITIVE LOGITS
    idious
    0.18
    -paced
    0.17
    aneous
    0.16
    éĢŁ
    0.15
     speed
    0.14
     paced
    0.14
    aneously
    0.14
     speeds
    0.13
    -fire
    0.13
     turnaround
    0.12
    Activations Density 1.241%

    No Known Activations