© 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. 42004
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åħ¨ä½ĵåijĺå·¥
    -0.09
    æŃ»äºº
    -0.08
    éļİ
    -0.08
    istra
    -0.08
    åĪĨ许
    -0.08
    ksom
    -0.08
    chied
    -0.08
     ugyanis
    -0.08
     opini
    -0.08
     nata
    -0.08
    POSITIVE LOGITS
    ium
    0.07
     attainment
    0.06
    çĶĺéľ²
    0.06
    对äºİ
    0.06
    å¯Įè´µ
    0.06
     satisfied
    0.06
    æĪĺçķ¥çĽ®æłĩ
    0.06
    enn
    0.06
    åºĩ
    0.06
    è¡£
    0.06
    Activations Density 0.000%

    No Known Activations