© 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. 1706
    Prev
    Next
    INDEX
    Explanations

    analyzing compounds

    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
    ç£IJ
    -0.07
    åħ¶ä»ĸæĸ¹å¼ı
    -0.06
    åħ¶ä»ĸåľ°æĸ¹
    -0.06
     Mechanics
    -0.06
     til
    -0.06
    til
    -0.06
    å¹²åĩĢæķ´æ´ģ
    -0.06
     Copp
    -0.06
    upert
    -0.06
    æľºåħ³
    -0.06
    POSITIVE LOGITS
    åĪĨåŃIJéĩı
    0.10
    åĪĨåŃIJ
    0.08
    æıIJåıĸ
    0.08
    lator
    0.08
    è¡ĢçĹĩ
    0.08
    æıIJåıĸçī©
    0.08
     brevet
    0.07
    èĶ¥
    0.07
     dissolved
    0.07
    沸çĤ¹
    0.07
    Activations Density 0.062%

    No Known Activations