© 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. 62630
    Prev
    Next
    INDEX
    Explanations

    safety restraints and occupant protection

    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
    èĩªæĿ¥æ°´
    -0.07
     поÑĩ
    -0.07
     hobby
    -0.06
    _TCP
    -0.06
     local
    -0.06
     perpet
    -0.06
    æŃĩ
    -0.06
    ore
    -0.06
    污水å¤ĦçIJĨ
    -0.06
    ost
    -0.06
    POSITIVE LOGITS
    å®īåħ¨å¸¦
    0.11
    åį±éļ¾
    0.10
    Ñħова
    0.09
    uyer
    0.09
     surviv
    0.09
    ëĿł
    0.08
     cint
    0.08
     vests
    0.08
    åįİéĺ³
    0.08
     vest
    0.08
    Activations Density 0.057%

    No Known Activations