© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48673
    Prev
    Next
    INDEX
    Explanations

    translation context

    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
    éij«
    -0.06
    å±ģèĤ¡
    -0.06
     sink
    -0.06
    ÙĦاس
    -0.06
    iht
    -0.06
    alem
    -0.06
     coefficient
    -0.06
    enner
    -0.06
    sink
    -0.06
     feel
    -0.06
    POSITIVE LOGITS
    æİĸ
    0.08
    ivist
    0.08
    cao
    0.07
    prima
    0.07
    éĶ¦æłĩ
    0.07
     useClass
    0.07
    USED
    0.07
    jew
    0.07
    å©ķ
    0.07
    ermo
    0.07
    Activations Density 0.002%

    No Known Activations