© 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. 64402
    Prev
    Next
    INDEX
    Explanations

    discontinuity or jumps

    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
    çĶ¸çĶ¸
    -0.10
    ergia
    -0.09
    å±ĪæĮĩ
    -0.08
    aning
    -0.08
    å®Ŀåħ¸
    -0.08
    erview
    -0.08
    äºĨä¸Ģéģį
    -0.08
    ë§ģ
    -0.08
    erti
    -0.08
    à¤Łà¤°
    -0.08
    POSITIVE LOGITS
     discontin
    0.09
    å¤Ħ
    0.09
    /dis
    0.07
    åıijçĶŁåľ¨
    0.07
     brus
    0.07
    å¤ĦçļĦ
    0.07
    s
    0.07
     abrupt
    0.07
    å°±åľ¨è¿ĻéĩĮ
    0.07
     occurring
    0.07
    Activations Density 0.003%

    No Known Activations