© 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. 7852
    Prev
    Next
    INDEX
    Explanations

    canon, denied, closing, exist, day

    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
    âĢ¦),
    -0.08
    æŁ¥åĩº
    -0.08
    inhos
    -0.08
    ?”,
    -0.08
    azos
    -0.08
    )**,
    -0.08
    åĬłæĭ¿å¤§
    -0.07
    æĹ¥ä»¥æĿ¥
    -0.07
    ANDLE
    -0.07
    idf
    -0.07
    POSITIVE LOGITS
    çIJĨçĶ±æĺ¯
    0.08
    ãĢĤ
    0.07
    çIJĨçĶ±
    0.06
    ยศ
    0.06
    çļĦä¾ĭåŃIJ
    0.06
    çIJĨçĶ±ãģ¯
    0.06
    .
    0.06
    çļĦçIJĨçĶ±
    0.06
    åıįä¹ĭ
    0.06
     comm
    0.06
    Activations Density 0.032%

    No Known Activations