© 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. 58033
    Prev
    Next
    INDEX
    Explanations

    phen

    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
    çĺ¦
    -0.07
    éľĨ
    -0.07
    ä¸Ńæĸ¹
    -0.07
    æ¸ħåģ¿
    -0.06
     serv
    -0.06
    rogram
    -0.06
    æ¸ħç®Ĺ
    -0.06
    è¾Ľèĭ¦äºĨ
    -0.06
    ustus
    -0.06
    å°ıéĿĴ
    -0.06
    POSITIVE LOGITS
    zep
    0.09
    ¹
    0.08
    ếp
    0.08
    ogat
    0.08
    _blocking
    0.08
    ä¹³
    0.08
     ÏĢαÏģά
    0.08
    _controls
    0.07
    以å¢ŀåĬł
    0.07
     ricer
    0.07
    Activations Density 0.008%

    No Known Activations