© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23170
    Prev
    Next
    INDEX
    Explanations

    other

    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¿ħ
    -0.07
    åµĮå¥Ĺ
    -0.07
    cle
    -0.07
    lech
    -0.07
    reh
    -0.07
     Kut
    -0.06
    angk
    -0.06
    è¡¥çŁŃ
    -0.06
    ang
    -0.06
    ìłĪ
    -0.06
    POSITIVE LOGITS
    类似çļĦ
    0.08
    åIJĮç±»
    0.08
    éľĦ
    0.08
     ÙħشابÙĩ
    0.08
    åIJĮæľŁ
    0.08
    asser
    0.08
    similar
    0.08
     similarly
    0.08
    ente
    0.07
    åIJĮ为
    0.07
    Activations Density 0.404%

    No Known Activations