© 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. 56100
    Prev
    Next
    INDEX
    Explanations

    later confirmed

    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
    æѤåĪ»
    -0.12
     currently
    -0.11
    çİ°åľ¨è¿ĺ
    -0.10
    çİ°åľ¨å¼Ģå§ĭ
    -0.10
    缮åīįæľī
    -0.10
    缮åīįå·²
    -0.10
    缮åīį
    -0.10
     bisher
    -0.10
    å½ĵä¸ĭçļĦ
    -0.09
    é¦ĸåħĪéľĢè¦ģ
    -0.09
    POSITIVE LOGITS
     Later
    0.10
    æł¹æį®éľĢè¦ģ
    0.10
     later
    0.10
    åıijå±ķ为
    0.09
    åıijå±ķæĪIJ为
    0.09
    Later
    0.09
    åıijå±ķæĪIJ
    0.09
    æĢİä¹Īæł·äºĨ
    0.09
    éĻĨç»Ń
    0.08
    later
    0.08
    Activations Density 0.180%

    No Known Activations