© 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. 29354
    Prev
    Next
    INDEX
    Explanations

    code structure and programming

    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
    ype
    -0.08
    _PHASE
    -0.08
    åı¯å¥¹
    -0.07
    åĪ©
    -0.07
    olin
    -0.07
    ricks
    -0.07
    è¾Ĺ
    -0.07
    oli
    -0.07
    ä¸įèµ·
    -0.07
    ATAR
    -0.07
    POSITIVE LOGITS
    æĦĪ
    0.08
    asang
    0.07
    对身ä½ĵ
    0.07
    apun
    0.07
    .plist
    0.07
    çģ
    0.07
    aille
    0.06
     herst
    0.06
     alike
    0.06
    /blue
    0.06
    Activations Density 0.026%

    No Known Activations