© 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. 56749
    Prev
    Next
    INDEX
    Explanations

    relative clauses and conditionals

    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
    angk
    -0.08
    çŃīåIJĦç±»
    -0.07
     Anc
    -0.07
     ense
    -0.07
    andes
    -0.07
    ardy
    -0.07
    çŃīåIJĦ
    -0.07
    eldes
    -0.07
    jeta
    -0.06
    åİ»ä½ķ
    -0.06
    POSITIVE LOGITS
     somehow
    0.12
     möglichst
    0.08
    æĹ¢èĥ½
    0.07
    whose
    0.07
    åıĪèĥ½
    0.07
    æīįè¡Į
    0.07
     whose
    0.07
    æ¯Ķå¦Ĥ
    0.07
     BOTH
    0.07
    è¿Ľåİ»
    0.06
    Activations Density 0.138%

    No Known Activations