© 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. 24075
    Prev
    Next
    INDEX
    Explanations

    sports, travel, medical conditions, religion, finance

    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
    loor
    -0.07
     alast
    -0.06
    uger
    -0.06
     ish
    -0.06
     Hin
    -0.06
     überhaupt
    -0.06
    æľ¬æ¥¼
    -0.06
    éľ
    -0.06
    erior
    -0.06
    osterone
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.11
    çŃīçī¹æ®Ĭ
    0.09
    çŃīé¢ĨåŁŁçļĦ
    0.08
    ãĢģ
    0.08
    çŃīåIJĦç±»
    0.08
     ÙħØ«ÙĦا
    0.07
    ä¸ĵ项
    0.07
    ãĢģãĢģ
    0.07
    маÑĤÑĭ
    0.07
     chẳng
    0.07
    Activations Density 0.236%

    No Known Activations