© 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. 45542
    Prev
    Next
    INDEX
    Explanations

    avoided, never, just, confirm, refusal

    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
    为äºĨæıIJé«ĺ
    -0.07
     inefficient
    -0.07
    ovski
    -0.07
    赶è¶ħ
    -0.07
     Neg
    -0.07
    eson
    -0.07
    oup
    -0.07
    inus
    -0.07
    为äºĨæĽ´å¥½çļĦ
    -0.07
    ernet
    -0.07
    POSITIVE LOGITS
    åĽŀéģ¿
    0.10
    çĤ¹åĪ°
    0.08
    æĹłå®³
    0.08
    æķıæĦŁçļĦ
    0.08
     decency
    0.07
    å¹³åĴĮ
    0.07
    è¶Ĭæĺ¯
    0.07
    æķıæĦŁ
    0.07
    undefined
    0.07
    juries
    0.07
    Activations Density 0.006%

    No Known Activations