© 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. 33833
    Prev
    Next
    INDEX
    Explanations

    Stimulus followed by Field or Technical

    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
    ilik
    -0.08
    wali
    -0.07
    åħ¶å¯¹
    -0.07
    æłijä¸ĬçļĦ
    -0.06
    iel
    -0.06
    ernet
    -0.06
    ?q
    -0.06
    izin
    -0.06
    对å¾ħ
    -0.06
     sid
    -0.06
    POSITIVE LOGITS
    示æĦıåĽ¾
    0.12
    åĽ¾ä¸Ń
    0.11
    åľĸ
    0.11
    示æĦı
    0.11
    åĽ¾
    0.10
     diagram
    0.10
    æŀ¶æŀĦåĽ¾
    0.10
    åĽ¾çļĦ
    0.10
    åĽ¾åĴĮ
    0.09
     photograph
    0.09
    Activations Density 0.108%

    No Known Activations