© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2783
    Prev
    Next
    INDEX
    Explanations

    license, code, or instructions

    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
    ä¼´ä½ł
    -0.09
    éĢ¢
    -0.07
    åĽ°
    -0.07
    -animate
    -0.07
     PROPERTY
    -0.07
    å¾¹åºķ
    -0.06
    Meet
    -0.06
    -"
    -0.06
    ç»®
    -0.06
    éľĢè¦ģè¿Ľè¡Į
    -0.06
    POSITIVE LOGITS
    è¿ĺæľīæľºä¼ļ
    0.08
    为éĩį
    0.08
    kit
    0.07
    å¾Ĺ天
    0.07
    jev
    0.07
     infer
    0.07
    fst
    0.07
    yss
    0.07
    çĥ§
    0.07
    该款
    0.07
    Activations Density 0.002%

    No Known Activations