© 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. 46624
    Prev
    Next
    INDEX
    Explanations

    served as controls

    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
    éĵ¿
    -0.08
    _util
    -0.07
    linger
    -0.07
    æ¯ĵ
    -0.07
    ère
    -0.07
    mig
    -0.06
    jer
    -0.06
     melip
    -0.06
    å¤ļç§įæĸ¹å¼ı
    -0.06
    åĽ½åĨħ
    -0.06
    POSITIVE LOGITS
    对çħ§ç»Ħ
    0.11
    对çħ§
    0.11
     subtract
    0.11
     subtraction
    0.10
    baseline
    0.10
    Baseline
    0.10
     baseline
    0.10
    æıIJä¾ĽåıĤèĢĥ
    0.09
    æī£éĻ¤
    0.09
     Bas
    0.09
    Activations Density 0.106%

    No Known Activations