© 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. 51816
    Prev
    Next
    INDEX
    Explanations

    career, booming, response, problem, experience, review, drive, war, axis

    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
    æĪĸåħ¶å®ĥ
    -0.07
    utri
    -0.07
    jä
    -0.06
    θÏħ
    -0.06
    æIJŃä¸Ĭ
    -0.06
    ãģ£ãģŁãĤĬ
    -0.06
    iÄħ
    -0.06
    æīį好
    -0.06
    .decorate
    -0.06
    retti
    -0.06
    POSITIVE LOGITS
    主è¦ģä½ĵçİ°åľ¨
    0.09
     пÑĥÑĤем
    0.08
    主è¦ģåĮħæĭ¬
    0.08
    西æľį
    0.08
    主è¦ģ表çİ°åľ¨
    0.08
    åħ·ä½ĵæĿ¥è¯´
    0.07
     whereby
    0.07
     à¹Ĥà¸Ķยมี
    0.07
    ä½ĵçİ°åľ¨
    0.07
     wherein
    0.07
    Activations Density 0.377%

    No Known Activations