© 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. 17921
    Prev
    Next
    INDEX
    Explanations

    a way to streamline

    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
    udes
    -0.08
    coni
    -0.08
    мба
    -0.08
    áĥIJáĥ®
    -0.07
    знÑı
    -0.07
    umé
    -0.07
    æĹłæ³ķ满足
    -0.07
    Encryption
    -0.07
    ostat
    -0.07
    мка
    -0.07
    POSITIVE LOGITS
    æŁIJäºĽ
    0.08
     smarter
    0.08
    æľīæĽ´
    0.07
    æĽ´é«ĺæķĪ
    0.07
    raj
    0.07
    ãĤĤãģ£ãģ¨
    0.07
    åĪ©çĶ¨
    0.07
    ä¼ļæĽ´å¥½
    0.07
     táºŃn
    0.07
    è¯ĨåĪ«
    0.07
    Activations Density 0.097%

    No Known Activations