© 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. 21093
    Prev
    Next
    INDEX
    Explanations

    Rearrange equations for coefficients

    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
    flight
    -0.08
    éķ¿æŀª
    -0.07
    wing
    -0.07
    -tool
    -0.07
    _bid
    -0.07
    ring
    -0.07
    wap
    -0.07
    Ñħоз
    -0.07
    顺å¿ĥ
    -0.07
    íĽ¼
    -0.07
    POSITIVE LOGITS
    常æķ°
    0.08
    没äºĭ
    0.08
     Fixed
    0.08
    Fixed
    0.08
    导读
    0.08
    交åıĭ
    0.07
     fixed
    0.07
    åĽºå®ļçļĦ
    0.07
    Constants
    0.07
     initializes
    0.07
    Activations Density 0.089%

    No Known Activations