© 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. 17389
    Prev
    Next
    INDEX
    Explanations

    rule, analytic, coupled

    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
     Me
    -0.06
    Me
    -0.06
    iers
    -0.06
     Parm
    -0.06
    och
    -0.06
    ä¾ĭ
    -0.06
    ixin
    -0.06
    irme
    -0.06
    odia
    -0.06
    åħ·æľīä¸Ģå®ļ
    -0.06
    POSITIVE LOGITS
    swer
    0.09
    åİ»ä½ķ
    0.09
     derivation
    0.08
    usy
    0.08
     bowiem
    0.08
    éĩĮåħĭ
    0.08
    没æľīæŶéĹ´
    0.08
    ç³ľ
    0.08
    ousel
    0.07
    .rl
    0.07
    Activations Density 0.055%

    No Known Activations