© 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. 16851
    Prev
    Next
    INDEX
    Explanations

    voltage or volt

    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
    æŀī
    -0.09
    æ¯Ķä¾ĭ为
    -0.08
    æ¯Ķä¾ĭçļĦ
    -0.08
    weights
    -0.08
    tones
    -0.08
    Ùģار
    -0.07
    æľīåģ¿
    -0.07
    ihak
    -0.07
    (CG
    -0.07
     proportions
    -0.07
    POSITIVE LOGITS
    åĩij
    0.07
    çķ¥
    0.07
    åħ¸
    0.06
    å°ĸ
    0.06
    ogl
    0.06
    Minimum
    0.06
    çIJ³
    0.06
    ìº
    0.06
    å°ĸçļĦ
    0.06
    çĿ¿
    0.06
    Activations Density 0.005%

    No Known Activations