© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14364
    Prev
    Next
    INDEX
    Explanations

    cited reference [@B1]

    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
    港澳åı°
    -0.08
    æľĢæĸ°è¯Ħ论
    -0.07
    æĮ«
    -0.07
    DAQ
    -0.07
    çĬ¯äºĨ
    -0.07
    dao
    -0.07
    åij¤
    -0.07
    康çĨĻåŃĹåħ¸
    -0.07
    ä¹Łå¹¶ä¸į
    -0.07
    émon
    -0.07
    POSITIVE LOGITS
     $\
    0.06
     foregoing
    0.06
    arus
    0.06
     --
    0.06
    åħ¬åħ±é¢Ħç®Ĺ
    0.06
     ---
    0.06
    æĭ¥æľīçĿĢ
    0.06
     ðŁ
    0.06
    æĺĮ
    0.06
    ä¾Ŀ
    0.05
    Activations Density 0.377%

    No Known Activations