© 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. 34668
    Prev
    Next
    INDEX
    Explanations

    success rate, low, high

    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
    æ¯įåŃIJ
    -0.07
    èIJ½å®ŀ好
    -0.07
    OperationException
    -0.07
    夫妻
    -0.07
    /loader
    -0.06
     Å¡
    -0.06
    è¿Ļåľºæ¯ĶèµĽ
    -0.06
    è¿ĻäºĽä¿¡æģ¯
    -0.06
    ooke
    -0.06
    å¿ĥä¸ŃçļĦ
    -0.06
    POSITIVE LOGITS
    å¢ĥçļĦ
    0.08
    客
    0.07
     dicon
    0.07
    çĵ¦å°Ķ
    0.07
    пÑĮ
    0.07
    alach
    0.07
    ujan
    0.07
    _algo
    0.07
    rror
    0.06
    VEL
    0.06
    Activations Density 0.016%

    No Known Activations