© 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. 33080
    Prev
    Next
    INDEX
    Explanations

    form or structure

    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
    ãģĿãĤį
    -0.08
    ä¸ĩæĪ·
    -0.08
    ×ķר×Ļ
    -0.07
    çĶĺ
    -0.07
    argin
    -0.07
    绾ç»İ
    -0.07
    rant
    -0.07
    اراÙĨ
    -0.07
    为æİ¨è¿Ľ
    -0.07
    æľĪåľ¨
    -0.07
    POSITIVE LOGITS
    æīĢéľĢçļĦ
    0.08
     formed
    0.07
    å¿ĥå¿ĥ
    0.07
     daraus
    0.07
     formation
    0.07
    orp
    0.06
    æīĢéľĢè¦ģçļĦ
    0.06
    çĶ±åIJĦ
    0.06
    æĺ¯ä¸įåı¯èĥ½çļĦ
    0.06
    #{@
    0.06
    Activations Density 0.028%

    No Known Activations