© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59078
    Prev
    Next
    INDEX
    Explanations

    beginning of sentence

    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
    Negative Logits
    鹦
    -0.07
    ÑĬ
    -0.07
    çļĦä¸Ģæĸ¹
    -0.07
    ss
    -0.07
    steen
    -0.07
    è§Ĩéķľ
    -0.06
    ights
    -0.06
    ãĤ¤ãĥ³ãĥĪ
    -0.06
    -ignore
    -0.06
    ipher
    -0.06
    POSITIVE LOGITS
    俱ä¹IJéĥ¨
    0.11
    缸è¾ħ缸æĪIJ
    0.10
    åĭĩå¾Ģ缴åīį
    0.10
    åħ¢åħ¢ä¸ļä¸ļ
    0.09
    æĸ°åĬłåĿ¡
    0.09
    åĬłæĭ¿å¤§
    0.09
    uncan
    0.08
    æĤ¨åı¯èĥ½
    0.08
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.08
    ogar
    0.07
    Activations Density 0.147%

    No Known Activations