© 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. 31690
    Prev
    Next
    INDEX
    Explanations

    effect, phenomenon

    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
    adal
    -0.08
    ä¸ī份
    -0.08
    OrDefault
    -0.07
    éĻ¤äºĨè¦ģ
    -0.07
    çļĦæ¸ħ
    -0.07
    å°Ķå¤ļ
    -0.07
    ád
    -0.07
     Vorgaben
    -0.07
    ateg
    -0.07
    IDEO
    -0.07
    POSITIVE LOGITS
    çݰ象
    0.20
     phenomena
    0.19
     phenomenon
    0.19
    çı¾è±¡
    0.16
    è¿Ļç§įçݰ象
    0.15
    çļĦçݰ象
    0.15
    çŃīçݰ象
    0.14
     Ñıвление
    0.14
     phénomène
    0.12
     ÑıвлениÑı
    0.12
    Activations Density 0.113%

    No Known Activations