© 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. 30569
    Prev
    Next
    INDEX
    Explanations

    legal citations and technical notation

    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
    ijľ
    -0.07
    çģ¯ç®±
    -0.07
    SETS
    -0.07
    rah
    -0.07
    å°ıåħµ
    -0.07
    elib
    -0.07
    -assets
    -0.07
    _ge
    -0.07
     intval
    -0.07
    è¾ĥ强
    -0.07
    POSITIVE LOGITS
    åĢŁ
    0.06
    ä¸Ģå¤ķ
    0.06
     EDUCA
    0.06
    è¿Ķ
    0.06
    åģ·
    0.06
    åijĬ
    0.06
     rab
    0.06
    æĽ¦
    0.06
    åħĶ
    0.06
    auff
    0.06
    Activations Density 0.057%

    No Known Activations