© 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. 46668
    Prev
    Next
    INDEX
    Explanations

    section numbers and references

    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
     @}
    -0.09
    åıªä»£è¡¨
    -0.09
    ä¸į代表
    -0.09
    owell
    -0.08
    ijľ
    -0.08
    éré
    -0.08
    erci
    -0.08
    MBED
    -0.08
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    -0.08
    HashCode
    -0.08
    POSITIVE LOGITS
    ï¼ļ“
    0.15
    åĨĻéģĵ
    0.13
    ï¼ļ"
    0.10
     “âĢ¦
    0.10
    :
    0.09
    åĨħ容为
    0.08
    æĽ°
    0.08
     "...
    0.08
    :"
    0.08
    ":"
    0.08
    Activations Density 0.043%

    No Known Activations