© 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. 50064
    Prev
    Next
    INDEX
    Explanations

    if it were

    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
    ify
    -0.08
    ive
    -0.08
    å¦ĤæŀľçĶ¨
    -0.08
    å¦Ĥæŀľä½łæĥ³
    -0.07
    äºĨåIJĹ
    -0.07
    æķ¬
    -0.07
    ervlet
    -0.07
    inari
    -0.07
    ä¹ĭæīĢ以
    -0.07
    los
    -0.07
    POSITIVE LOGITS
     siquiera
    0.09
    çĦ¶å¤§
    0.07
    交æīĢ
    0.07
    akan
    0.07
    anced
    0.07
    çĦ¶æĺ¯
    0.07
    æĿ¥å¾ĹåıĬ
    0.07
    ä¹Łåĥı
    0.07
    å°Ķçī¹
    0.07
    Sharper
    0.07
    Activations Density 0.023%

    No Known Activations