© 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. 13402
    Prev
    Next
    INDEX
    Explanations

    route, path, walk, sequence

    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¦Ĥæŀľè§īå¾Ĺ
    -0.07
    inu
    -0.07
     боло
    -0.07
     Factory
    -0.07
     Bast
    -0.07
    缴æİ¥ä¸İ
    -0.07
    缴æݥ被
    -0.06
     tiers
    -0.06
    åıĹåĪ°å½±åĵį
    -0.06
    å¾Ĺè¿ĩ
    -0.06
    POSITIVE LOGITS
    èµ·æŃ¢
    0.10
    ç»ĪçĤ¹
    0.09
    路线
    0.09
    è¡Ķ
    0.09
     sequence
    0.09
    èµ·å§ĭ
    0.08
    è§ħ
    0.08
    åºıåĪĹ
    0.08
     seq
    0.08
    sequence
    0.08
    Activations Density 0.009%

    No Known Activations