© 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. 34175
    Prev
    Next
    INDEX
    Explanations

    lock, unlock, open, close

    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
    Compiler
    -0.08
    Stretch
    -0.08
    amik
    -0.07
    ä¸įç®Ģåįķ
    -0.07
    ãĤŃãĥ£ãĥĥãĤ·ãĥ¥
    -0.07
    讨
    -0.07
    ikat
    -0.07
    æĬĬè¿ĻäºĽ
    -0.07
     expressive
    -0.07
    å¿ĥå¢ĥ
    -0.07
    POSITIVE LOGITS
    解éĻ¤
    0.10
    åºĶæĢ¥
    0.09
    èĩªåĬ¨
    0.09
     automatic
    0.09
     imminent
    0.09
     autonom
    0.08
    å®īåħ¨åı¯éĿł
    0.08
     automatically
    0.08
    çŁŃæļĤ
    0.08
     safely
    0.08
    Activations Density 0.140%

    No Known Activations