© 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. 43842
    Prev
    Next
    INDEX
    Explanations

    contrasting or alternative options

    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
    夷
    -0.06
    :#
    -0.06
    çŁ
    -0.06
     найд
    -0.06
    ä¸Ģå®ļ
    -0.06
    astian
    -0.06
    æĦ
    -0.06
    é£
    -0.06
    athy
    -0.06
    ather
    -0.06
    POSITIVE LOGITS
     hingegen
    0.12
    缸æ¯Ķä¹ĭä¸ĭ
    0.12
     merely
    0.11
    åĪĻä¼ļ
    0.10
     dagegen
    0.10
     meanwhile
    0.10
    çŃīåħ¶ä»ĸ
    0.10
     natomiast
    0.10
    ä½ľåĪĻ
    0.09
    åĪĻæĺ¯
    0.09
    Activations Density 0.027%

    No Known Activations