© 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. 20353
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    å¨ĺ家
    -0.06
    idl
    -0.06
    rine
    -0.06
    stw
    -0.06
    ิà¸Ķ
    -0.06
    nali
    -0.06
    ัà¸ģ
    -0.06
    ÙĦاÙħ
    -0.06
    ambi
    -0.06
    éŨä¸ĭ
    -0.06
    POSITIVE LOGITS
    çļĦåħ¶ä»ĸ
    0.12
    åħ¶ä»ĸæĸ¹å¼ı
    0.12
    åħ¶å®ĥ
    0.10
    ä»»ä½ķåħ¶ä»ĸ
    0.10
    åħ¶ä»ĸ
    0.10
     lainnya
    0.10
     sonstige
    0.10
    åħ¶ä»ĸçļĦ
    0.09
    åħ¶å®ĥçļĦ
    0.09
     вообÑīе
    0.09
    Activations Density 1.008%

    No Known Activations