© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46523
    Prev
    Next
    INDEX
    Explanations

    particularly to

    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
    opol
    -0.07
    opoulos
    -0.07
    mack
    -0.06
    weed
    -0.06
    gens
    -0.06
    SCI
    -0.06
    æ¢ħèĬ±
    -0.06
    ENS
    -0.06
    epam
    -0.06
    顾ä¸įä¸Ĭ
    -0.06
    POSITIVE LOGITS
    å¾ĢåIJİ
    0.07
    ì°©
    0.07
    åħĭæĸ¯
    0.07
    ukk
    0.07
    èľĤ
    0.07
     Mol
    0.07
    OnError
    0.07
    ajuan
    0.07
    çĸ¯çĭĤçļĦ
    0.07
    é»ĺ
    0.07
    Activations Density 0.004%

    No Known Activations