© 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. 40809
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    log
    -0.07
    éķľ
    -0.07
    /../
    -0.06
    è¯Ĩ
    -0.06
    å¿Į
    -0.06
    ç»Ļ人们
    -0.06
     ment
    -0.06
    entic
    -0.06
    tru
    -0.06
    ilyn
    -0.06
    POSITIVE LOGITS
    éĩįéĩį
    0.08
    icos
    0.08
    åħ®
    0.08
    åĪĨéĻ¢
    0.07
    åĭĩå¾Ģ缴åīį
    0.07
    oksi
    0.07
    çī¹åĪ«æĺ¯å¯¹
    0.07
    åħ¶ä¹IJ
    0.07
    ×Ļ×IJ
    0.07
    udi
    0.07
    Activations Density 0.025%

    No Known Activations