© 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. 63289
    Prev
    Next
    INDEX
    Explanations

    selenium-based crystals

    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
    -lite
    -0.09
    %@
    -0.08
    çľĭä¸į
    -0.07
    íĺķìĿĦ
    -0.07
     Fiorent
    -0.07
    ết
    -0.07
    ä¾ĿçĦ¶åŃĺåľ¨
    -0.07
    รร
    -0.07
    iddy
    -0.07
     getattr
    -0.07
    POSITIVE LOGITS
    cule
    0.08
    akah
    0.08
    hou
    0.07
     ex
    0.07
    cik
    0.07
    hak
    0.07
    ä¸įæĭĶ
    0.07
     Tou
    0.07
    è´¯
    0.07
    ä¸ĩå¤ļ
    0.06
    Activations Density 0.032%

    No Known Activations