© 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. 65109
    Prev
    Next
    INDEX
    Explanations

    encrypt/decrypt, synthesis, translation, recovery

    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
    illah
    -0.09
    oire
    -0.08
    èĢģçĪ¸
    -0.08
    iak
    -0.07
    LIC
    -0.07
    ìĦľê´Ģ
    -0.07
    çī¹å°Ķ
    -0.07
    ItemCount
    -0.07
     FED
    -0.07
    rani
    -0.07
    POSITIVE LOGITS
    èĢĮå¤į
    0.09
    復
    0.08
    è¿ĶåĽŀ
    0.08
    åĽŀæĿ¥
    0.08
    å¤įåİŁ
    0.08
    å¤į
    0.08
     round
    0.08
    ãģ«æĪ»
    0.07
     recover
    0.07
     recovery
    0.07
    Activations Density 0.014%

    No Known Activations