© 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. 32559
    Prev
    Next
    INDEX
    Explanations

    by default my filters selection

    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
    缪
    -0.07
     ante
    -0.07
    飬
    -0.07
    åĺ¿
    -0.06
    åĸ½
    -0.06
    attes
    -0.06
    ifest
    -0.06
    ishes
    -0.06
    å¾ĹæĦı
    -0.06
    说çļĦ
    -0.06
    POSITIVE LOGITS
     tehát
    0.10
    æīĢæľīè¿ĻäºĽ
    0.09
     therefore
    0.09
     inoltre
    0.09
    åĽłæѤ
    0.09
     insomma
    0.09
    ä¹Łåı¯èĥ½æĺ¯
    0.08
    ovich
    0.08
     infine
    0.08
     donc
    0.08
    Activations Density 0.008%

    No Known Activations