© 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. 42834
    Prev
    Next
    INDEX
    Explanations

    question prompts

    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
    å°Ĥ
    -0.07
    èijĹ
    -0.07
    oug
    -0.07
    iggins
    -0.07
     Reliable
    -0.06
    ibert
    -0.06
    謳
    -0.06
    æĺıè¿·
    -0.06
    mack
    -0.06
    åĪ©å¤ļ
    -0.06
    POSITIVE LOGITS
    è°ľåºķ
    0.09
    żÄħ
    0.08
    StdString
    0.08
    ר×ķף
    0.07
     clever
    0.07
    bildungen
    0.07
    åĢĻè£ľ
    0.07
    ünkü
    0.07
    ENTITY
    0.07
    æ±Łæ²³
    0.07
    Activations Density 0.003%

    No Known Activations