© 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. 48841
    Prev
    Next
    INDEX
    Explanations

    unrelated or ineffective

    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
    á»įi
    -0.07
    缺çĤ¹æĺ¯
    -0.07
    ä¸įèĭŁ
    -0.07
    ICHE
    -0.06
     downside
    -0.06
    çŀ»
    -0.06
    oles
    -0.06
    ä¿¡ãģĺ
    -0.06
    alls
    -0.06
    opal
    -0.06
    POSITIVE LOGITS
     irrelevant
    0.13
     unrelated
    0.11
    æĹłåħ³
    0.10
     superficial
    0.10
    ä¸įå±ŀäºİ
    0.09
    ä¸įæŀĦæĪIJ
    0.09
    ä¸įèĥ½ä½ľä¸º
    0.08
    æĮīçħ§åĽ½å®¶
    0.08
     mere
    0.08
     ineffective
    0.08
    Activations Density 0.148%

    No Known Activations