© 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. 44917
    Prev
    Next
    INDEX
    Explanations

    mathematical examples and substitutions

    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
    ä¾ĭå¦Ĥ
    -0.08
    æľīä¸ĢäºĽ
    -0.07
    åıĹçļĦ
    -0.07
    ä½Ĩè¿ĻäºĽ
    -0.07
    åľ¨ä¸ĢäºĽ
    -0.07
    ä¸ĢäºĽéĹ®é¢ĺ
    -0.07
    åħ·æľī以ä¸ĭ
    -0.06
    ä¾ĭãģĪãģ°
    -0.06
    çĿĢåij¢
    -0.06
    æĮīçħ§åĽ½å®¶
    -0.06
    POSITIVE LOGITS
    gev
    0.08
     messageId
    0.07
    arna
    0.07
    -vs
    0.07
    æľ¬è´¨
    0.07
    å·§å¦Ļåľ°
    0.07
     оказÑĭваеÑĤÑģÑı
    0.07
    ÐłÐ¡
    0.07
    èIJ½èĦļ
    0.07
    å°¸
    0.07
    Activations Density 0.001%

    No Known Activations