© 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. 45202
    Prev
    Next
    INDEX
    Explanations

    corresponds to math, hypothesis, or quantities

    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
    å¯¹ä½łçļĦ
    -0.07
    ovas
    -0.07
    åı¯æĺ¯æĪij
    -0.06
    èĽĭ
    -0.06
     merit
    -0.06
    wig
    -0.06
     grund
    -0.06
    ayers
    -0.06
     Exempl
    -0.06
    ç¬Ķ
    -0.06
    POSITIVE LOGITS
     corresponds
    0.10
    åħ¶å®ŀå°±æĺ¯
    0.10
    å°±çĽ¸å½ĵäºİ
    0.10
     corresponde
    0.09
     corres
    0.09
    ä¼ļåıĺæĪIJ
    0.09
    对åºĶ
    0.08
     Correspond
    0.08
    çĽ¸å¯¹åºĶ
    0.08
    å°±åıĺæĪIJäºĨ
    0.08
    Activations Density 0.037%

    No Known Activations