© 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. 15639
    Prev
    Next
    INDEX
    Explanations

    essentially, effectively, basically

    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
    åħ·ä½ĵæŶéĹ´
    -0.09
    åħ·ä½ĵ
    -0.08
     justement
    -0.08
    åħ·ä½ĵåĨħ容
    -0.08
    åħ·ä½ĵè¦ģæ±Ĥ
    -0.08
     moreover
    -0.08
    åĪĩå®ŀç»´æĬ¤
    -0.08
    eres
    -0.07
     supposedly
    -0.07
    åħ·ä½ĵéĹ®é¢ĺ
    -0.07
    POSITIVE LOGITS
    entially
    0.11
    åıĺ缸
    0.09
    åįĬ个
    0.09
    Ùĭ
    0.08
    ãģ®ãģ¨ãģĵãĤį
    0.07
    mente
    0.07
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.07
    åľ°æĬĬ
    0.07
    ãģŁãģı
    0.07
    åįĬ
    0.07
    Activations Density 0.033%

    No Known Activations