© 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. 61896
    Prev
    Next
    INDEX
    Explanations

    location of elements

    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
     nämlich
    -0.09
    ãģłãģijãģ§ãģªãģı
    -0.07
    è¡ĮåĬ¨èµ·æĿ¥
    -0.07
    emd
    -0.07
    并ä¸į容æĺĵ
    -0.07
    ÙİÙijØ°
    -0.06
    fahr
    -0.06
     bá»ĥ
    -0.06
     zwar
    -0.06
     Desp
    -0.06
    POSITIVE LOGITS
    éļıä¹ĭ
    0.10
     accordingly
    0.09
     thereafter
    0.09
    亦çĦ¶
    0.09
     thereof
    0.09
    ä¹Łéļıä¹ĭ
    0.09
     meanwhile
    0.08
    åĪĻ以
    0.08
     theirs
    0.08
    为è¾ħ
    0.08
    Activations Density 0.107%

    No Known Activations