© 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. 28289
    Prev
    Next
    INDEX
    Explanations

    technical tool or component

    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
    çŃīéĩįè¦ģ
    -0.07
     bách
    -0.07
    对äºİä¸ĢäºĽ
    -0.06
    æģ¶åĬ¿åĬĽ
    -0.06
    çŃī主è¦ģ
    -0.06
     Messe
    -0.06
    çŃī诸å¤ļ
    -0.06
    ä½ľä¸ºä¸Ģ项
    -0.06
    ç»Ļ人以
    -0.06
    ä¿¡æģ¯ä»ħä¾ĽåıĤèĢĥ
    -0.06
    POSITIVE LOGITS
    诸å¦Ĥ
    0.10
    æ¯Ķå¦Ĥ
    0.10
     вÑĢоде
    0.10
    ä¾ĭå¦Ĥ
    0.09
    å¦Ĥ
    0.08
    ãģŁãģ¨ãģĪãģ°
    0.08
    Õ¹
    0.08
    èѬå¦Ĥ
    0.08
     à¹Ģà¸Ĭà¹Īà¸Ļ
    0.08
     poput
    0.08
    Activations Density 0.032%

    No Known Activations