© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 24110
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    æĦıä¹īçļĦ
    -0.08
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.08
    ç¾İåī§
    -0.08
    }while
    -0.07
    &q
    -0.07
    esan
    -0.07
    æ³ķçŃī
    -0.07
    rolled
    -0.07
    两个维æĬ¤
    -0.07
    æĢ»åı°
    -0.07
    POSITIVE LOGITS
    示
    0.07
    æķ´çIJĨ
    0.06
    ymb
    0.06
    对çħ§
    0.06
    æħķ
    0.06
    uria
    0.06
     oppon
    0.06
    表çİ°
    0.06
    zy
    0.05
    足
    0.05
    Activations Density 0.029%

    No Known Activations