© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30070
    Prev
    Next
    INDEX
    Explanations

    result finding males villas

    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
    Į¨
    -0.09
    _fake
    -0.08
    ä¸ĢæıIJ
    -0.08
    Ñıви
    -0.07
    è¿ĻäºĽä¸ľè¥¿
    -0.07
    SWEP
    -0.07
    [__
    -0.07
    åĽłä¸ºè¿Ļ
    -0.07
    dup
    -0.07
    CTYPE
    -0.07
    POSITIVE LOGITS
    çĶ±æѤåı¯è§ģ
    0.07
    åı¯çŁ¥
    0.07
    åı¯è§ģ
    0.06
     indeed
    0.06
    ç¡®å®ŀ
    0.06
    ouc
    0.06
    éŀł
    0.06
    *
    0.06
    [
    0.06
     vill
    0.06
    Activations Density 0.002%

    No Known Activations