© 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. 33993
    Prev
    Next
    INDEX
    Explanations

    parenthesized expressions

    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
    _lengths
    -0.07
     Bernd
    -0.07
    {text
    -0.07
    jit
    -0.07
     investe
    -0.07
    /*@
    -0.07
    /*/
    -0.07
    æ²¼
    -0.07
    çݩ转
    -0.07
    ifier
    -0.06
    POSITIVE LOGITS
    åĢ¼ä¸º
    0.08
    åĢ¤
    0.08
    /autoload
    0.07
    åĢ¼
    0.07
    ught
    0.07
    è®°å¿ĨçĬ¹
    0.07
    ê°Ĵ
    0.07
    ctions
    0.07
    lsa
    0.07
    åĢ¼æĺ¯
    0.07
    Activations Density 0.010%

    No Known Activations