© 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. 7412
    Prev
    Next
    INDEX
    Explanations

    constructor or variable 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
    maa
    -0.09
    brig
    -0.08
    éĹ»
    -0.08
    å¸Ĥå§Ķåī¯ä¹¦è®°
    -0.08
    icona
    -0.08
    ornos
    -0.08
    eman
    -0.08
    å¦Ĥæŀľåĩºçİ°
    -0.08
    çŁ¥åħ¶
    -0.08
    SIDE
    -0.08
    POSITIVE LOGITS
    åĪĿåѦèĢħ
    0.07
    çĽ
    0.06
    å·¨
    0.06
     sor
    0.06
     cop
    0.06
    0.06
    æĪ¸
    0.06
    wan
    0.06
    åĪĿ
    0.06
    åħĪçĶŁ
    0.06
    Activations Density 0.720%

    No Known Activations