© 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. 55310
    Prev
    Next
    INDEX
    Explanations

    conductivity

    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
    åĭĺ
    -0.09
    çŁ¥åħ¶
    -0.08
    centes
    -0.07
    rena
    -0.07
    udo
    -0.07
    äºĨ解èĩªå·±çļĦ
    -0.07
    æīįæĺ¯
    -0.07
    æīįæĺ¯æľĢ
    -0.07
    chte
    -0.07
    etil
    -0.07
    POSITIVE LOGITS
     constants
    0.08
    常éĩı
    0.07
    emp
    0.07
    pref
    0.07
    å©´
    0.07
    Constants
    0.07
    ูล
    0.06
    ãĤĴ表
    0.06
    纾
    0.06
    常æķ°
    0.06
    Activations Density 0.011%

    No Known Activations