© 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. 7838
    Prev
    Next
    INDEX
    Explanations

    word endings and subsequent completions

    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
    çįħ
    -0.08
     kerap
    -0.08
    第ä¸ĢæŶéĹ´
    -0.08
    γά
    -0.08
    估计
    -0.07
    çĭ®
    -0.07
     Habit
    -0.07
     تÙĤر
    -0.07
    ajari
    -0.07
    å¢ħ
    -0.07
    POSITIVE LOGITS
    åºĶå½ĵä¾Ŀçħ§
    0.08
    è¾¾åĪ°äºĨ
    0.07
     Somm
    0.07
     määrä
    0.06
    åģ¶
    0.06
    .rules
    0.06
    åıijå±ķ模å¼ı
    0.06
     odd
    0.06
    æĮĩæı®
    0.06
    å¿ħ须符åIJĪ
    0.06
    Activations Density 0.001%

    No Known Activations