© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8913
    Prev
    Next
    INDEX
    Explanations

    locomotive and vehicles

    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
    /angular
    -0.07
     lente
    -0.07
     Peters
    -0.06
    篱
    -0.06
    çĨŁ
    -0.06
    éĴĵ
    -0.06
     synth
    -0.06
    riz
    -0.06
    å°ıæľ¨
    -0.06
    çĭ¬
    -0.06
    POSITIVE LOGITS
     boarding
    0.09
    INLINE
    0.08
    ayload
    0.08
    è¡ĮæĿİ
    0.08
    undur
    0.08
    æ¶Ĥè£ħ
    0.08
    payload
    0.08
     crew
    0.08
    ä¸ĩåĽ½
    0.08
    -mounted
    0.07
    Activations Density 0.016%

    No Known Activations