© 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. 42174
    Prev
    Next
    INDEX
    Explanations

    falseč

    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
    åIJįå±±
    -0.07
    ÑģÑĤÑĭ
    -0.06
    Care
    -0.06
    è£ħ
    -0.06
    usah
    -0.06
    åĽłæĸ¯åĿ¦
    -0.06
    fred
    -0.06
    é«ĺ楼
    -0.06
    è§Ħ
    -0.06
    ucceed
    -0.06
    POSITIVE LOGITS
    è¡Įä¹ĭ
    0.08
    rano
    0.08
    说她
    0.08
    edir
    0.07
    adro
    0.07
    OGO
    0.07
    å¤ı侯
    0.07
    edt
    0.07
    对åѦçĶŁè¿Ľè¡Į
    0.07
    å°±æĺ¯è¿Ļä¹Ī
    0.07
    Activations Density 0.064%

    No Known Activations