© 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. 43852
    Prev
    Next
    INDEX
    Explanations

    steady state or error

    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
    æ°Ľ
    -0.09
    aes
    -0.08
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.08
    ä¹±çļĦ
    -0.08
    rowned
    -0.08
     vX
    -0.08
    å¤ĸéĺ´
    -0.08
    (ix
    -0.08
    æĺĵçĪĨ
    -0.08
    éĺ²æݧæݪæĸ½
    -0.07
    POSITIVE LOGITS
    缴æµģ
    0.08
     steady
    0.08
    steady
    0.07
    稳
    0.07
    å¹³
    0.07
    æĹłç©·
    0.06
    ราà¸ļ
    0.06
    èĢĥäºĨ
    0.06
    çĶĺéľ²
    0.06
     forever
    0.06
    Activations Density 0.008%

    No Known Activations