© 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. 43459
    Prev
    Next
    INDEX
    Explanations

    commonly, frequently, often

    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
    ivi
    -0.08
    åĪ»éª¨éĵŃ
    -0.08
    缴æİ¥çļĦ
    -0.07
    åİŁåıijæĢ§
    -0.07
    egro
    -0.07
    åľ¨çľī
    -0.07
    ادرة
    -0.07
    .Dir
    -0.07
    è¯ķçĤ¹
    -0.07
    Ľ°
    -0.07
    POSITIVE LOGITS
    常çĶ¨äºİ
    0.13
    常çĶ¨çļĦ
    0.12
     ubiquitous
    0.11
    常çĶ¨
    0.11
     commonly
    0.11
     often
    0.11
    å¹¿æ³ĽçĶ¨äºİ
    0.11
    å¹¿æ³ĽåºĶçĶ¨äºİ
    0.10
    ç»ıå¸¸åľ¨
    0.10
     frequently
    0.10
    Activations Density 0.296%

    No Known Activations