© 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. 9272
    Prev
    Next
    INDEX
    Explanations

    death penalty sentencing

    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
    转载请
    -0.09
     spontan
    -0.08
    èĩªæķij
    -0.08
     spok
    -0.08
    åĻª
    -0.08
    guer
    -0.08
     Reinh
    -0.07
    æ±Ĥæķij
    -0.07
    æºī
    -0.07
    åľ°åĿĢä½įäºİ
    -0.07
    POSITIVE LOGITS
    åī¥å¤º
    0.09
     forfeiture
    0.09
     inflict
    0.08
    æī§è¡ĮçļĦ
    0.08
    å¨ģæħij
    0.08
     outcomes
    0.08
    åĬĽåº¦
    0.08
     sentencing
    0.08
     imprisonment
    0.08
     inflicted
    0.08
    Activations Density 0.041%

    No Known Activations