© 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. 41078
    Prev
    Next
    INDEX
    Explanations

    RR or Mr followed by number/equals

    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
    %B
    -0.07
     ([]
    -0.07
    è¶Ĭå¤ļ
    -0.07
    اÙĨÙĬ
    -0.07
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.06
     ("%
    -0.06
    æĪIJç«ĭ
    -0.06
    ului
    -0.06
    åĪ©çĽĬçļĦ
    -0.06
    atoren
    -0.06
    POSITIVE LOGITS
    缸åħ³éĹ®çŃĶ
    0.07
    åĪĨåĪ«ä¸º
    0.07
    oms
    0.07
    约为
    0.07
    erschaft
    0.07
    ezÅij
    0.07
    çĻ¾å·Ŀ
    0.07
    ä»ħ为
    0.07
    obj
    0.07
    OMO
    0.07
    Activations Density 0.025%

    No Known Activations