© 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. 60970
    Prev
    Next
    INDEX
    Explanations

    industrial chemicals and compounds

    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
    uci
    -0.07
    wh
    -0.07
    ä¸į足以
    -0.06
    _SHARED
    -0.06
    elsey
    -0.06
    ogl
    -0.06
    goo
    -0.06
    jou
    -0.06
    éħ¥
    -0.06
    æ¶ĪåĮĸåIJ¸æĶ¶
    -0.06
    POSITIVE LOGITS
     desired
    0.10
    éľĢè¦ģä»İ
    0.09
     coveted
    0.09
     via
    0.09
    desired
    0.09
     меÑĤодом
    0.09
     needed
    0.09
    çļĦéĩįè¦ģéĢĶå¾Ħ
    0.08
     пÑĥÑĤем
    0.08
     urgently
    0.08
    Activations Density 0.236%

    No Known Activations