© 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. 3233
    Prev
    Next
    INDEX
    Explanations

    three, 3, triples, triple

    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
     miss
    -0.07
     sol
    -0.07
    å²±
    -0.06
    éĢıè¿ĩ
    -0.06
    ÏĦοÏį
    -0.06
    tai
    -0.06
    ôn
    -0.06
    æ£Ģ讨
    -0.06
    unker
    -0.06
    对çĹĩä¸ĭèį¯
    -0.06
    POSITIVE LOGITS
     pairwise
    0.10
    åıĤä¸İçļĦ
    0.09
    åıĤä¸İæ´»åĬ¨
    0.09
    åıĤä¸İåĪ°
    0.08
    åıĤä¸İåħ¶ä¸Ń
    0.08
    åıĤä¸İ
    0.08
    ]+)/
    0.08
    åıĥèĪĩ
    0.08
     ketiga
    0.08
    åıĤä¸İ度
    0.08
    Activations Density 0.065%

    No Known Activations