© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37784
    Prev
    Next
    INDEX
    Explanations

    importance or necessity

    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
    使çĶ¨çļĦæĺ¯
    -0.08
    æĺ¯æĢİä¹ĪåĽŀäºĭ
    -0.08
    åı¯éĩĩçĶ¨
    -0.08
    使çĶ¨äºĨ
    -0.07
    koch
    -0.07
     utilizando
    -0.07
    èµ°åIJijäºĨ
    -0.07
    齿
    -0.07
     Pole
    -0.07
    ä»»çĶ¨
    -0.07
    POSITIVE LOGITS
    еÑĩаÑĤ
    0.08
    amid
    0.08
    æľīè¯Ŀ
    0.08
    çļĦåİŁåĽł
    0.07
    èIJ½çļĦ
    0.07
    åıijå±ķçļĦéľĢè¦ģ
    0.06
    缴æİ¥åħ³ç³»åĪ°
    0.06
    orado
    0.06
    对çħ§
    0.06
    çİĩé«ĺ
    0.06
    Activations Density 0.079%

    No Known Activations