© 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. 58241
    Prev
    Next
    INDEX
    Explanations

    Route definition

    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
    alse
    -0.07
    رائ
    -0.07
    æķ²éŨ
    -0.07
    é£ĺ
    -0.07
    arana
    -0.06
    è°§
    -0.06
    มà¸Ļา
    -0.06
    æīĢçĶ¨çļĦ
    -0.06
    upy
    -0.06
    .getBytes
    -0.06
    POSITIVE LOGITS
    å®ĥ为
    0.09
    åħ¶ä¸º
    0.08
    otá
    0.07
    ä¸ĢæŀĿ
    0.07
    #=
    0.07
    æľīçļĦæĺ¯
    0.07
    enth
    0.07
    ?=
    0.07
    inst
    0.07
    ạm
    0.07
    Activations Density 0.001%

    No Known Activations