© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8717
    Prev
    Next
    INDEX
    Explanations

    multiples of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    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
    ikian
    -0.08
    itere
    -0.08
    –and
    -0.08
    Ắ
    -0.08
    对æѤä¸įæī¿æĭħä»»ä½ķ
    -0.08
    eggi
    -0.08
    дела
    -0.08
    _aux
    -0.08
    apatan
    -0.07
    äºĭåıij
    -0.07
    POSITIVE LOGITS
     Ryan
    0.06
     life
    0.06
    åħĭå°Ķ
    0.06
     Fare
    0.06
    μοÏįÏĤ
    0.05
    aise
    0.05
    Ian
    0.05
    alous
    0.05
    大çĪ·
    0.05
     ÑĤек
    0.05
    Activations Density 0.001%

    No Known Activations