© 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. 32080
    Prev
    Next
    INDEX
    Explanations

    conclusion and inference indicators

    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¦Ĥä½ķåĪ©çĶ¨
    -0.07
    çļĦä¸Ģç³»åĪĹ
    -0.07
    ikal
    -0.07
    å¦Ĥä½ķéĢļè¿ĩ
    -0.07
    çIJĨ顺
    -0.07
    å¦Ĥä½ķ解åĨ³
    -0.06
     ÑĥпÑĢа
    -0.06
    æķĻä½łå¦Ĥä½ķ
    -0.06
    ä¹ĭéķ¿
    -0.06
    è¦ģå¦Ĥä½ķ
    -0.06
    POSITIVE LOGITS
    ledes
    0.08
     íķ´ëĭ¹
    0.07
    该款
    0.07
    æŃ¤èµ·
    0.06
    oop
    0.06
    .codes
    0.06
    rud
    0.06
    (?)
    0.06
    æĢ»ä½ĵä¸Ĭ
    0.06
    OLOR
    0.06
    Activations Density 0.006%

    No Known Activations