© 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. 61428
    Prev
    Next
    INDEX
    Explanations

    illness or drug

    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
    ergeb
    -0.09
    MK
    -0.08
    _COMPILE
    -0.07
    èĤĩ
    -0.07
    èĻ½çĦ¶çİ°åľ¨
    -0.07
    lien
    -0.07
     MK
    -0.07
    ãng
    -0.07
    erten
    -0.07
    çº¢é¢ľ
    -0.07
    POSITIVE LOGITS
     unrelated
    0.12
     Simply
    0.09
     baseline
    0.09
     artifact
    0.09
     simply
    0.08
    baseline
    0.08
     inherent
    0.08
    æľ¬èº«
    0.08
    Baseline
    0.08
    çª
    0.08
    Activations Density 0.211%

    No Known Activations