© 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. 26025
    Prev
    Next
    INDEX
    Explanations

    each, each, each

    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
    åĮħ
    -0.07
    ocene
    -0.07
    ep
    -0.07
    opal
    -0.07
    åIJĬ
    -0.07
    annel
    -0.07
    åī¥
    -0.07
    å¾ĢæĹ¥
    -0.07
    åı¸
    -0.07
    èĤĮ
    -0.07
    POSITIVE LOGITS
     costly
    0.10
    æĪIJæľ¬é«ĺ
    0.09
     impr
    0.08
     manageable
    0.08
    夯
    0.08
    å°ıè§Ħ模
    0.08
    æĺĤè´µçļĦ
    0.08
    å°½éĩıå°ij
    0.08
    æĪĸåĪ©çĶ¨
    0.08
    代价
    0.08
    Activations Density 0.215%

    No Known Activations