© 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. 61801
    Prev
    Next
    INDEX
    Explanations

    choice or comparison

    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
    Ø´Ùģ
    -0.08
    ä¹ĭ以
    -0.07
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.07
    ietta
    -0.07
    ansi
    -0.07
    ielen
    -0.07
    ruck
    -0.07
    oman
    -0.07
    çĮ¬
    -0.07
    以åıĬåħ¶ä»ĸ
    -0.07
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.13
    èĢĮéĿŀ
    0.13
     rather
    0.12
    ãģ»ãģĨ
    0.10
    rather
    0.09
     plutôt
    0.09
    ãģ®æĸ¹ãģĮ
    0.08
     쪽
    0.08
     piuttosto
    0.08
    éĤ£è¾¹
    0.08
    Activations Density 0.115%

    No Known Activations