© 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. 30442
    Prev
    Next
    INDEX
    Explanations

    hydrocarbons

    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
     accordingly
    -0.07
    æĥ³ä½ł
    -0.07
    arlo
    -0.06
     Branco
    -0.06
    arne
    -0.06
    å°±æѤ
    -0.06
    缸åºĶ
    -0.06
    å®ĥè¿ĺ
    -0.06
    éĤ£ä¸ª
    -0.06
    èĩ³æѤ
    -0.06
    POSITIVE LOGITS
    åıĪ称
    0.10
    atham
    0.09
    顾åIJįæĢĿä¹ī
    0.08
    åıĪåIJį
    0.08
    ][/
    0.08
    ä¸ĵä¸ļä»İäºĭ
    0.08
    ↵        ↵        ↵
    0.08
    "},"
    0.08
    oger
    0.08
    alkan
    0.08
    Activations Density 0.006%

    No Known Activations