© 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. 3492
    Prev
    Next
    INDEX
    Explanations

    intention or intent

    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
    ORA
    -0.07
     Liberties
    -0.07
    åĪĹ
    -0.07
    ×Ĺ×Ļ
    -0.06
    åĽ½å®¶åĴĮåľ°åĮºçļĦ
    -0.06
    ues
    -0.06
    ingatkan
    -0.06
    gree
    -0.06
    æķĻä¼ļ
    -0.06
     <<=
    -0.06
    POSITIVE LOGITS
    æĦıåĽ¾
    0.18
     intent
    0.18
     intentions
    0.18
     intention
    0.17
    intent
    0.15
     Intent
    0.15
     motives
    0.15
     intents
    0.14
    Intent
    0.14
     intención
    0.14
    Activations Density 0.045%

    No Known Activations