© 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. 40166
    Prev
    Next
    INDEX
    Explanations

    depends on or is proportional

    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
    éĻĮ
    -0.07
    éľĦ
    -0.07
    æĹłè¯¯
    -0.07
    æĹłåıĮ
    -0.07
    åį³å°Ĩ
    -0.07
    ancock
    -0.07
    çĸij
    -0.07
    ä¾ĭå¤ĸ
    -0.07
    orial
    -0.06
    çī¹æ®ĬæĥħåĨµ
    -0.06
    POSITIVE LOGITS
    åıĸåĨ³äºİ
    0.15
    depends
    0.14
     depends
    0.13
     depending
    0.12
    Depending
    0.11
     завиÑģиÑĤ
    0.11
     depended
    0.11
     Depends
    0.11
    depending
    0.11
     depend
    0.10
    Activations Density 0.088%

    No Known Activations