© 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. 7517
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by auxiliary verb or possessive

    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
    æĦĪåĬł
    -0.08
     requisite
    -0.08
    åħ¶åľ¨
    -0.07
     myriad
    -0.07
     deemed
    -0.07
     necess
    -0.07
    æĦĪåıij
    -0.07
    jen
    -0.07
     deline
    -0.07
     aforementioned
    -0.07
    POSITIVE LOGITS
    ãĤ³ãĥ¬
    0.08
    ä¸Ģèµ·åŃ¦ä¹ł
    0.08
    #index
    0.08
    ặn
    0.08
     ðŁij
    0.08
     Khang
    0.08
    å¯¹ä½łæľī帮åĬ©
    0.08
     meetup
    0.08
    amac
    0.08
    ç®ĢåįķæĿ¥è¯´
    0.08
    Activations Density 0.069%

    No Known Activations