© 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. 34255
    Prev
    Next
    INDEX
    Explanations

    website, nursery, viagra, SEO, ramadan, spark, investment, door, travelling, kitchen

    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
    åħ±åIJĮ为
    -0.08
    klen
    -0.08
    ãģĤãģŁ
    -0.08
    teria
    -0.07
    aros
    -0.07
    maids
    -0.07
    cante
    -0.07
    çĥŃçĥĪç¥Ŀè´º
    -0.07
    RICS
    -0.07
    ople
    -0.07
    POSITIVE LOGITS
    å°±åĥı
    0.07
    éĩįåľ¨
    0.07
    åIJ®
    0.07
    esar
    0.06
    ph
    0.06
    æĺ¯ä¸Ģçīĩ
    0.06
    è¦ģ注æĦı
    0.06
    å®´
    0.06
    äºĮåŃĹ
    0.06
    lv
    0.06
    Activations Density 0.021%

    No Known Activations