© 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. 63831
    Prev
    Next
    INDEX
    Explanations

    0 degrees

    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
    į°
    -0.08
    人åij½
    -0.08
    pañ
    -0.08
    æĤī
    -0.08
    å·¥èµĦçļĦ
    -0.08
    วà¸ģ
    -0.08
    STD
    -0.08
    ivain
    -0.07
    ÑħаÑĢ
    -0.07
    å±ħå¤ļ
    -0.07
    POSITIVE LOGITS
    ores
    0.07
    /
    0.06
    aper
    0.06
    åįķè¾¹
    0.06
    ç©¿éĢı
    0.06
    ç©¿è¿ĩ
    0.06
     or
    0.06
    éĢıè§Ĩ
    0.06
    /A
    0.06
    °
    0.06
    Activations Density 0.005%

    No Known Activations