© 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. 63620
    Prev
    Next
    INDEX
    Explanations

    satisfied or null

    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
    转贴
    -0.09
    Alias
    -0.08
    hill
    -0.08
     seper
    -0.08
     CALLBACK
    -0.08
    alias
    -0.08
    resh
    -0.08
    acap
    -0.08
    éķ¿æľŁä»İäºĭ
    -0.08
    egi
    -0.07
    POSITIVE LOGITS
     satisfied
    0.09
    æĢİä¹Ī说
    0.08
    空
    0.08
     trivial
    0.08
    atisfied
    0.08
     silence
    0.07
    空çĻ½
    0.07
     satisfy
    0.07
     sil
    0.07
     silent
    0.07
    Activations Density 0.005%

    No Known Activations