© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26998
    Prev
    Next
    INDEX
    Explanations

    anger, displeasure, negative emotions

    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
    æ·±è¿ľ
    -0.08
    裳
    -0.08
     mirac
    -0.08
    浸润
    -0.07
    èĥĨåŃIJ
    -0.07
    ken
    -0.07
    éĢłåģĩ
    -0.07
    æŁĶå¼±
    -0.07
    -doc
    -0.06
    çīµ
    -0.06
    POSITIVE LOGITS
    èĦ¾æ°Ķ
    0.12
    æĢĴ
    0.12
    åıijæ³Ħ
    0.12
     angrily
    0.11
    æĮĩè´£
    0.11
     ÑĢаздÑĢа
    0.11
    æĦ¤æĢĴ
    0.11
    åıijèĦ¾æ°Ķ
    0.10
    è¾±éªĤ
    0.10
    ä¸įèĢIJçĥ¦
    0.10
    Activations Density 0.377%

    No Known Activations