© 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. 1008
    Prev
    Next
    INDEX
    Explanations

    shrub, climbing, herb, growing plant

    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
    apt
    -0.07
    [Test
    -0.06
    ä¼¼æĺ¯
    -0.06
    åĸī
    -0.06
    æ±½
    -0.06
     payload
    -0.06
    èĤ¤
    -0.06
    éªĮ
    -0.06
    éĻįèIJ½
    -0.06
    å¿ħèĥľ
    -0.06
    POSITIVE LOGITS
    éĢIJå¹´
    0.10
    磮
    0.09
    éĢ¸
    0.09
    å¤ļå¹´
    0.09
    æķ°å¹´
    0.09
     kompak
    0.08
    缴ç«ĭ
    0.08
    èĩ¥
    0.08
     yearly
    0.08
     tahunan
    0.08
    Activations Density 0.039%

    No Known Activations