© 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. 31877
    Prev
    Next
    INDEX
    Explanations

    documentation, user, request, problem, resource

    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
    UCH
    -0.07
    uje
    -0.07
    æľīåºıæİ¨è¿Ľ
    -0.07
    ç¹¼
    -0.06
    ائÙĦ
    -0.06
    äºĶåĪĨéĴŁ
    -0.06
    æĪij们ä»Ĭ天
    -0.06
    erb
    -0.06
    pictured
    -0.06
    åħ³æ³¨åĴĮ
    -0.06
    POSITIVE LOGITS
     moreover
    0.09
    åħ¶å®ĥ
    0.09
    çĦ¶åIJİæł¹æį®
    0.08
    çĦ¶åIJİ
    0.08
    åĽłæѤ
    0.08
     Moreover
    0.08
     Therefore
    0.08
    åħ¶å®ĥçļĦ
    0.07
    åħ¶ä»ĸ人
    0.07
    ä¸ĢæĹ¦è¢«
    0.07
    Activations Density 0.261%

    No Known Activations