© 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. 23004
    Prev
    Next
    INDEX
    Explanations

    appellee/ Appellee's

    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
     Escr
    -0.08
    _EXTERN
    -0.08
    omod
    -0.08
    YPE
    -0.08
    æĪijçļĦå·¥ä½ľ
    -0.08
    addtogroup
    -0.07
    Ïģια
    -0.07
    涨è·Į
    -0.07
    redo
    -0.07
    éĻĦ带
    -0.07
    POSITIVE LOGITS
     nim
    0.06
    移åĪ°
    0.06
    ifer
    0.06
    åĽłç´ł
    0.06
     contribution
    0.06
     numerator
    0.06
     denominator
    0.06
    äk
    0.06
    ä¸īä¸Ģ
    0.06
    åħ°è¾¾
    0.06
    Activations Density 0.004%

    No Known Activations