© 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. 38705
    Prev
    Next
    INDEX
    Explanations

    check with your

    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
    ëıħ
    -0.07
    _globals
    -0.07
    æ²»çĹħ
    -0.07
    arre
    -0.06
    侦
    -0.06
    jaz
    -0.06
    æ£ĢæµĭåĪ°
    -0.06
    нал
    -0.06
    ä¸Ģéĥ¨åĪĨ
    -0.06
    èĻ½çĦ¶åľ¨
    -0.06
    POSITIVE LOGITS
    å½ĵåľ°çļĦ
    0.10
    å½ĵåľ°
    0.10
    ä¸İå½ĵåľ°
    0.08
    çķ¶åľ°
    0.08
    èİ·åıĸ
    0.08
     definit
    0.08
     consult
    0.08
     اÙĦÙħØŃÙĦÙĬØ©
    0.08
    åľ¨ä»ĸ们çļĦ
    0.08
     local
    0.08
    Activations Density 0.080%

    No Known Activations