© 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. 4525
    Prev
    Next
    INDEX
    Explanations

    polarity and direction

    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
    å¹³åĿĩæ¯ı
    -0.08
    æĪĸå¤ļæĪĸå°ij
    -0.07
    inato
    -0.07
    ÑĢÑĥÑĤ
    -0.07
    åijĽ
    -0.07
    ring
    -0.07
    zend
    -0.07
    æĹ©çĿ¡
    -0.07
    æķĻäºİ
    -0.06
    è¿Ļå°ıåŃIJ
    -0.06
    POSITIVE LOGITS
     discharge
    0.08
    æłĩè¯Ĩ
    0.08
    telen
    0.07
    imony
    0.07
    æĶ¾çĶµ
    0.07
     polarity
    0.07
    leston
    0.07
     ë°ĺëĮĢ
    0.07
     opposite
    0.07
    è´Łæŀģ
    0.07
    Activations Density 0.005%

    No Known Activations