© 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. 24081
    Prev
    Next
    INDEX
    Explanations

    /LICENSE following certain text

    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
    atab
    -0.08
    çİĩè¾¾åĪ°
    -0.06
     picture
    -0.06
     Hull
    -0.06
    onya
    -0.06
     Ethics
    -0.06
     compens
    -0.05
     Heb
    -0.05
    ãĤĴçĻº
    -0.05
    æĺ¯åĪ©çĶ¨
    -0.05
    POSITIVE LOGITS
    quam
    0.08
    ivant
    0.08
    形形èī²
    0.08
    oins
    0.08
    owie
    0.07
    ùi
    0.07
    ,list
    0.07
    ifter
    0.07
    ÙĪØ´
    0.07
    _docs
    0.07
    Activations Density 0.007%

    No Known Activations