© 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. 57925
    Prev
    Next
    INDEX
    Explanations

    dear, for, working, mystery, new, well, right, chord

    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
    eke
    -0.08
    å¾ĹçĽĬ
    -0.07
    izeit
    -0.07
    ÙĦاØŃ
    -0.06
    çĶļæĺ¯
    -0.06
    uras
    -0.06
    ä¹ĺçĿĢ
    -0.06
     keren
    -0.06
    羨
    -0.06
    äºĨä¸įèµ·
    -0.06
    POSITIVE LOGITS
    对æĪijæĿ¥è¯´
    0.13
     ÙĦدÙī
    0.12
     bagi
    0.12
    åľ¨æĪijå¿ĥä¸Ń
    0.12
     باÙĦÙĨسبة
    0.12
     chez
    0.11
     мне
    0.11
     Bagi
    0.10
    对æĪij
    0.10
    åľ¨æĪijçļĦ
    0.10
    Activations Density 0.493%

    No Known Activations