© 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. 4122
    Prev
    Next
    INDEX
    Explanations

    CELER, boost, units, acceleration

    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
    tron
    -0.08
    èĩªå·±çļĦ缮æłĩ
    -0.08
    -target
    -0.07
    ãĤ¿ãĥ¼ãĤ²ãĥĥãĥĪ
    -0.07
    _TARGET
    -0.07
    Targets
    -0.07
    å®Ŀå¦Ī
    -0.07
     led
    -0.07
    targets
    -0.07
     targets
    -0.06
    POSITIVE LOGITS
    æĹłéĩı
    0.08
    æĹłæģĻ
    0.08
    åĬĽ
    0.07
    度éĩı
    0.07
    æĪijæĺİçĻ½äºĨ
    0.07
    æµģ
    0.07
    redi
    0.07
    åĬ¨è¾Ħ
    0.07
    _units
    0.07
    ä¼
    0.07
    Activations Density 0.002%

    No Known Activations