© 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. 24401
    Prev
    Next
    INDEX
    Explanations

    insane, fucking, shitty, crappy

    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
     loh
    -0.08
    å¹´ä»ħ
    -0.08
    -reply
    -0.08
    æĽ¾åĽł
    -0.08
    ä¹ĭ忧
    -0.08
    ;!
    -0.08
    èĩªå·±çļĦçĶŁåij½
    -0.07
    ä¼ĺç§Ģä½ľæĸĩ
    -0.07
    ä¸įæĸĻ
    -0.07
    leftright
    -0.07
    POSITIVE LOGITS
     fucking
    0.09
     freaking
    0.09
     kinda
    0.09
    /
    0.09
    ãģ£ãģ¦ãĤĭ
    0.08
     pissed
    0.08
    -ish
    0.08
    (?)
    0.08
     crappy
    0.08
     fucked
    0.08
    Activations Density 1.252%

    No Known Activations