© 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. 65151
    Prev
    Next
    INDEX
    Explanations

    indulgence in sugar and sedentary behavior

    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
    åģļ好äºĭ
    -0.08
     Avis
    -0.07
    èĮ«
    -0.07
    尿裤
    -0.07
    çļĦ温æļĸ
    -0.07
    ç»ĵåĨ°
    -0.07
    羸åŃIJ
    -0.07
    /lists
    -0.07
     persecuted
    -0.07
    ibre
    -0.07
    POSITIVE LOGITS
    æĪIJçĺ¾
    0.11
     addictive
    0.10
    çļĦåį±å®³
    0.10
     indul
    0.09
     binge
    0.09
    umsuz
    0.09
     indulge
    0.09
    èĩ´çĻĮ
    0.09
     excessive
    0.09
    çŃīä¸įèī¯
    0.08
    Activations Density 0.099%

    No Known Activations