© 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. 48067
    Prev
    Next
    INDEX
    Explanations

    negative connotations or opinions

    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
    è¯Ī
    -0.07
     autent
    -0.06
    _generic
    -0.06
    CG
    -0.06
    urgi
    -0.06
    æĪijç»Ļ
    -0.06
    è©IJ
    -0.06
    (iter
    -0.06
    หมุà¸Ļ
    -0.06
    æ£
    -0.06
    POSITIVE LOGITS
    åIJ¦å®ļ
    0.10
    æŀģ端
    0.10
     phủ
    0.09
    åħ¶è§ĤçĤ¹
    0.09
    æŀģ强çļĦ
    0.09
     denying
    0.08
     extreme
    0.08
    åī¥å¤º
    0.08
     restrictive
    0.08
     ekstrem
    0.08
    Activations Density 0.044%

    No Known Activations