© 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. 20593
    Prev
    Next
    INDEX
    Explanations

    false/true booleans

    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
    è¬
    -0.08
    .insertBefore
    -0.07
    ball
    -0.07
    Serializable
    -0.06
     tout
    -0.06
    Ì
    -0.06
    æĢĸ
    -0.06
    æ¯
    -0.06
    å±±ç¾Ĭ
    -0.06
     itself
    -0.06
    POSITIVE LOGITS
    æĿ¡æĿ¡
    0.08
    jav
    0.08
    æĬĬä¸Ģ个
    0.08
    oze
    0.07
    æķĻäºİ
    0.07
    ÑİÑĢе
    0.07
    uria
    0.07
    ukul
    0.07
    æ¨Ł
    0.07
    osto
    0.07
    Activations Density 0.014%

    No Known Activations