© 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. 39566
    Prev
    Next
    INDEX
    Explanations

    corresponded with/generate a/systems such as/Castro/p-type

    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
     relent
    -0.07
    失æķĪ
    -0.07
    éļ¾æĢª
    -0.07
    etections
    -0.07
     nomine
    -0.07
    avig
    -0.07
    è¢«ä¾ĽåºĶåķĨ
    -0.07
    åİŁæĸĩ
    -0.07
    羣æŃ£çļĦ
    -0.07
    ç»ı纬
    -0.07
    POSITIVE LOGITS
    缸æ¯Ķäºİ
    0.08
    æ¯Ķèµ·æĿ¥
    0.08
    大ä¹ī
    0.08
    GOR
    0.07
    åĪ©çĶ¨äºĨ
    0.07
     акÑĤа
    0.07
    çļĦ好å¤Ħ
    0.07
    å¥ijåIJĪ
    0.07
    è¦ģæ¯Ķ
    0.07
    缸æ¯Ķä¹ĭä¸ĭ
    0.07
    Activations Density 0.007%

    No Known Activations