© 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. 23351
    Prev
    Next
    INDEX
    Explanations

    formats, methods, specifications

    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
    大ç¾İ
    -0.07
    repid
    -0.07
    缸åħ³æݨèįIJ
    -0.07
    yai
    -0.07
    Animating
    -0.07
     ability
    -0.07
    omentum
    -0.07
    ashian
    -0.07
    åĪ¶åº¦æĶ¹éĿ©
    -0.07
     ê²°ê³¼
    -0.07
    POSITIVE LOGITS
     permissible
    0.10
    以åıĬå¦Ĥä½ķ
    0.10
    å¦Ĥä½ķè¿Ľè¡Į
    0.09
     allowable
    0.09
     acceptable
    0.09
    è§Ħå®ļäºĨ
    0.09
    çŃīäºĭ项
    0.09
    ãģĦãģ¤
    0.09
     specifics
    0.08
     ÙĪØŃد
    0.08
    Activations Density 0.181%

    No Known Activations