© 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. 9762
    Prev
    Next
    INDEX
    Explanations

    word and languages

    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
    inale
    -0.08
    å¦Ĥæŀľä¸į
    -0.08
    illante
    -0.08
    endig
    -0.08
    øs
    -0.08
    æ·ĺæ±°
    -0.08
    æĪIJåĬŁåIJİ
    -0.08
     perfec
    -0.08
     judici
    -0.07
     successfully
    -0.07
    POSITIVE LOGITS
     word
    0.08
     relational
    0.07
     verb
    0.07
    ä¸Ģè¯į
    0.07
    ä¸ĢåŃĹ
    0.07
     scholarly
    0.07
    è¿Ļ个è¯į
    0.06
    åĬ¨è¯į
    0.06
    å½ĵåį³
    0.06
    Ľ
    0.06
    Activations Density 0.032%

    No Known Activations