© 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. 3101
    Prev
    Next
    INDEX
    Explanations

    lot of, someone, some

    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
    foundland
    -0.10
    nable
    -0.09
    æľīåħ³æĥħåĨµ
    -0.09
    æľīäºĨä¸Ģ个
    -0.08
    æľīåĬł
    -0.08
    æľīåħ³äºĭ项
    -0.08
    æľīéĹľ
    -0.08
    มีสà¹Īวà¸Ļรà¹Īวม
    -0.08
    theless
    -0.08
    æľīåħ³
    -0.08
    POSITIVE LOGITS
    æĶ¾çŁ¢
    0.15
    åĬ©äºİ
    0.08
    ÑģÑĤÑĥпление
    0.08
    i
    0.08
    s
    0.07
    種ãģ®
    0.07
    enus
    0.07
    zelfde
    0.07
    (y
    0.07
    entifier
    0.06
    Activations Density 0.002%

    No Known Activations