© 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. 63907
    Prev
    Next
    INDEX
    Explanations

    character strings and numbers

    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
    åIJįæĢĿ
    -0.10
     menyar
    -0.08
    åİ¿éķ¿
    -0.08
    pee
    -0.08
    bolo
    -0.08
    pron
    -0.08
    转载èĩ³
    -0.08
    seys
    -0.08
    ktop
    -0.08
    éĥ¨èIJ½å®¢
    -0.08
    POSITIVE LOGITS
    åİŁæľī
    0.08
    åİŁæĿ¥çļĦ
    0.07
    åİŁå§ĭ
    0.07
    _duplicate
    0.07
    åİŁæľīçļĦ
    0.07
    çĹħ
    0.06
    èĴĤ
    0.06
    alla
    0.06
    aus
    0.06
    åİŁå§ĭçļĦ
    0.06
    Activations Density 0.001%

    No Known Activations