© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50258
    Prev
    Next
    INDEX
    Explanations

    research publication announcements

    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
    allery
    -0.08
    indu
    -0.08
     ÙĤÙĬÙĦ
    -0.07
     supposedly
    -0.07
    zac
    -0.07
    landen
    -0.07
    umpf
    -0.07
    ÑĢоки
    -0.07
    声称
    -0.07
    elib
    -0.07
    POSITIVE LOGITS
    ãģ®ãģ¯
    0.07
     co
    0.07
    _AUTH
    0.06
    åIJĥæ³ķ
    0.06
    _CONFIGURATION
    0.06
    .cgi
    0.06
    人çĶŁçļĦ
    0.06
    庵
    0.06
    汪æ´ĭ
    0.06
    eras
    0.06
    Activations Density 1.160%

    No Known Activations