© 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. 22992
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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
    -0.08
    atement
    -0.06
    led
    -0.06
    ole
    -0.06
    rot
    -0.06
    æĿ¥åİĨ
    -0.06
    zz
    -0.06
    çļĦåĪ¶ä½ľæĸ¹æ³ķ
    -0.06
    ç«ĭæĸ°
    -0.06
    åĵģè¡Į
    -0.06
    POSITIVE LOGITS
    ¦
    0.09
    ãģĦãĤĮãģ°
    0.08
    åħ¨è·¯æ®µ
    0.08
    Ñĥн
    0.07
    æĮģä¹ĭ以
    0.07
    JAKARTA
    0.07
    inian
    0.07
    åħ¢åħ¢ä¸ļä¸ļ
    0.07
    ืà¹Īà¸Ńม
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    Activations Density 0.033%

    No Known Activations