© 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. 15983
    Prev
    Next
    INDEX
    Explanations

    two-pass, multistage, fallback

    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
     conveyed
    -0.07
    elf
    -0.07
    atham
    -0.06
    ç³»
    -0.06
    好åĿı
    -0.06
    ä¸įåıªæĺ¯
    -0.06
    è¯ļ
    -0.06
     conveying
    -0.06
    adam
    -0.06
    adari
    -0.06
    POSITIVE LOGITS
    åħĪçĶ¨
    0.10
     inexpensive
    0.09
    æķĪæŀľæĽ´å¥½
    0.09
     strategically
    0.09
     cheaper
    0.09
    èĢĮ对äºİ
    0.09
    è¾ħ以
    0.09
    ä½İé£İéĻ©
    0.08
    çļĦé«ĺæķĪ
    0.08
    ä½İæĪIJæľ¬
    0.08
    Activations Density 0.240%

    No Known Activations