© 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. 24995
    Prev
    Next
    INDEX
    Explanations

    forward. blessings. states. ology

    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
    indir
    -0.08
    insa
    -0.07
    æĥ³åĪ°è¿ĻéĩĮ
    -0.07
    _abort
    -0.07
    iac
    -0.07
    iola
    -0.07
    nat
    -0.07
    è§ģ人
    -0.06
    è¯·çĽ´æİ¥
    -0.06
    Ãło
    -0.06
    POSITIVE LOGITS
    åħ·ä½ĵæĿ¥è¯´
    0.07
    orex
    0.07
    强è°ĥçļĦæĺ¯
    0.07
    æį¢åı¥è¯Ŀ说
    0.07
    emas
    0.07
     Specifically
    0.06
    ä¹Łå°±æĺ¯è¯´
    0.06
    è¶ħè¿ĩ约
    0.06
    æĩĤ
    0.06
    就好åĥı
    0.06
    Activations Density 0.018%

    No Known Activations