© 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. 11388
    Prev
    Next
    INDEX
    Explanations

    back and forth

    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
    fried
    -0.08
    å°ijåħĪ
    -0.08
     Scre
    -0.07
    avance
    -0.07
    overflow
    -0.07
    eps
    -0.07
    æľīçĶŁ
    -0.07
    edig
    -0.07
     setC
    -0.07
    éĢĤé¾Ħ
    -0.06
    POSITIVE LOGITS
    åĽŀæĿ¥
    0.09
    à¸ģลัà¸ļ
    0.09
    éĢģåĽŀ
    0.09
    è¿ĶåĽŀ
    0.09
    å¾Ģè¿Ķ
    0.08
    -back
    0.08
     retr
    0.08
    -return
    0.08
    æĿ¥åĽŀ
    0.08
    ellet
    0.08
    Activations Density 0.009%

    No Known Activations