© 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. 32349
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs followed by verbs or adverbs

    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
    åħ¶çī¹å¾ģ
    -0.10
    åħ¶åľ¨
    -0.10
    åħ¶åİŁåĽł
    -0.09
    æĺ¯åħ¶
    -0.09
    对åħ¶è¿Ľè¡Į
    -0.08
    åħ¶
    -0.08
    åħ¶ä¸º
    -0.08
    åħ¶ä¸Ĭ
    -0.08
    使åħ¶
    -0.08
    åħ¶èº«
    -0.08
    POSITIVE LOGITS
     faut
    0.08
    èĢģ人家
    0.08
    chy
    0.08
    ä¸İåħ¶å®ĥ
    0.08
    ä¿©
    0.07
    inerary
    0.07
    zk
    0.07
    íݸ
    0.07
    /she
    0.07
     berdua
    0.07
    Activations Density 0.944%

    No Known Activations