© 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. 9960
    Prev
    Next
    INDEX
    Explanations

    SSL, port, substitute

    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
    byname
    -0.09
    osso
    -0.08
    à¯įப
    -0.08
    SEX
    -0.08
    ç¹°
    -0.08
    ẩn
    -0.08
    åĩºå¥ĩ
    -0.07
    _STRUCTURE
    -0.07
    alus
    -0.07
    æľī家
    -0.07
    POSITIVE LOGITS
    mirror
    0.07
    éķľ
    0.07
     mirror
    0.07
    uke
    0.07
    æĺ¯è¯¥
    0.07
    éĢĤ
    0.07
    éı¡
    0.06
    succ
    0.06
    éķľåĥı
    0.06
     represent
    0.06
    Activations Density 0.008%

    No Known Activations