© 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. 22180
    Prev
    Next
    INDEX
    Explanations

    stable / stability

    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
    æİĴéĩı
    -0.07
    бÑı
    -0.07
    åħ¨è¦ĨçĽĸ
    -0.07
     exclusively
    -0.07
     simult
    -0.07
     disap
    -0.07
    仪
    -0.07
    غط
    -0.07
    ä¸į使çĶ¨
    -0.07
    æŁĶè»Ł
    -0.07
    POSITIVE LOGITS
     stability
    0.15
     stable
    0.15
    稳å®ļæĢ§
    0.14
     Stability
    0.13
    稳å®ļçļĦ
    0.13
    稳å®ļ
    0.13
    çļĦ稳å®ļ
    0.12
    çĽ¸å¯¹ç¨³å®ļ
    0.11
    stable
    0.11
     Stable
    0.11
    Activations Density 0.014%

    No Known Activations