© 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. 16038
    Prev
    Next
    INDEX
    Explanations

    chemical product formation

    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
    zell
    -0.08
    SOURCE
    -0.08
    èı
    -0.07
     Source
    -0.07
    Source
    -0.07
    äºĶ常
    -0.07
    åħħæ²Ľ
    -0.07
     Vox
    -0.07
    _Source
    -0.06
     legendary
    -0.06
    POSITIVE LOGITS
     formation
    0.08
    ä¿ĿçķĻ
    0.08
     formed
    0.08
     Formation
    0.08
     forms
    0.08
    åij½åIJį为
    0.07
    ä¿ĿçķĻäºĨ
    0.07
    imer
    0.07
    å½¢å¼ı
    0.07
    èĥľ
    0.07
    Activations Density 0.048%

    No Known Activations