© 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. 25752
    Prev
    Next
    INDEX
    Explanations

    narrative themes

    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
    aring
    -0.06
    çļĦä¸ĢäºĽ
    -0.06
    orando
    -0.06
    çī¹åĪ«æĺ¯
    -0.06
    åıĬå®īåħ¨
    -0.06
    lig
    -0.06
    etim
    -0.06
    aran
    -0.05
    ientemente
    -0.05
    kenntnisse
    -0.05
    POSITIVE LOGITS
    ãĤĨãģı
    0.08
    imper
    0.08
    è¿ĩæĹ¥åŃIJ
    0.08
    पाल
    0.08
    å¸Ŀéĥ½
    0.07
    ivor
    0.07
    hver
    0.07
    ÙĪÙĦÙĬØ©
    0.07
     بدÙĦاÙĭ
    0.07
    èĢĮä¸įæĺ¯
    0.07
    Activations Density 0.025%

    No Known Activations