© 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. 26869
    Prev
    Next
    INDEX
    Explanations

    EOF and nil terminator

    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
    aign
    -0.07
     cont
    -0.07
    verno
    -0.07
    ine
    -0.07
    åĴ¬çīĻåĪĩ
    -0.07
    è¾IJ
    -0.06
     transcend
    -0.06
    ordinal
    -0.06
    Unsafe
    -0.06
    æ±ĩéĽĨ
    -0.06
    POSITIVE LOGITS
    éĽĢ
    0.08
    opes
    0.07
    ileo
    0.07
    æĸĩæĺİçļĦ
    0.07
    å°±ç»Ļ
    0.07
    arz
    0.07
     EOF
    0.07
    便
    0.07
     одн
    0.07
    סק
    0.07
    Activations Density 0.004%

    No Known Activations