© 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. 29541
    Prev
    Next
    INDEX
    Explanations

    conditional statements

    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
    acent
    -0.06
     likewise
    -0.06
    å¦ĤæŀľæĬĬ
    -0.06
     ìĹĨëĭ¤ëĬĶ
    -0.06
    缸æ¯Ķäºİ
    -0.06
    缸åIJĮçļĦ
    -0.06
    hof
    -0.06
    anco
    -0.06
    è£ģ
    -0.06
    é
    -0.06
    POSITIVE LOGITS
    åıªæĺ¯æĥ³
    0.08
    éĥ½æĥ³
    0.08
     unsure
    0.08
    ystore
    0.07
     unclear
    0.07
    æľīçĸijéĹ®
    0.07
    achel
    0.07
    +":
    0.07
    áĭ«
    0.07
     doute
    0.07
    Activations Density 0.132%

    No Known Activations