© 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. 40247
    Prev
    Next
    INDEX
    Explanations

    criteria, validators

    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
    czo
    -0.08
    æł¹æį®åħ¬åı¸
    -0.08
     reemb
    -0.07
    iture
    -0.07
    icas
    -0.07
    æĪij第ä¸Ģ次
    -0.07
    åĸľæĢĴ
    -0.07
    请åĴ¨è¯¢
    -0.07
    iscal
    -0.07
    okit
    -0.07
    POSITIVE LOGITS
    æĿ¡ä»¶åĴĮ
    0.08
    antara
    0.07
    çĶŁæ´»ä¸Ĭ
    0.07
    åĭ¾
    0.06
     Criteria
    0.06
    validators
    0.06
     Lieb
    0.06
    主è§Ĥ
    0.06
    kus
    0.06
     criteria
    0.06
    Activations Density 0.001%

    No Known Activations