© 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. 24076
    Prev
    Next
    INDEX
    Explanations

    be followed by adjective or participle

    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
    rant
    -0.07
    åĨįçĶŁèĥ½æºIJ
    -0.07
     khÄĥn
    -0.07
     nhÆ°á»Ŀng
    -0.07
    éĽ¯
    -0.07
    ä½łä¸Ģ个
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    ØŃØ©
    -0.07
    æĸ¯åį¡
    -0.07
     jota
    -0.07
    POSITIVE LOGITS
     able
    0.10
     unable
    0.08
    ieve
    0.08
    ceive
    0.07
    stride
    0.07
     ÙĤادر
    0.07
    /be
    0.07
    ä¹ĭæ°Ķ
    0.07
     indifferent
    0.07
    åĽłç´łå½±åĵį
    0.07
    Activations Density 0.818%

    No Known Activations