© 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. 45316
    Prev
    Next
    INDEX
    Explanations

    code structure elements

    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
    вив
    -0.08
    ä¸įä½ıäºĨ
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    éĵIJ
    -0.08
    irut
    -0.08
    inges
    -0.08
    <|im_start|>
    -0.08
    å¤įåĪ¶éĵ¾æİ¥
    -0.08
    é¾Ļæ±Ł
    -0.07
    è´Ńè¿Ľ
    -0.07
    POSITIVE LOGITS
     finally
    0.08
    oug
    0.06
     vel
    0.06
    硬
    0.06
    hist
    0.06
    çĤ¸
    0.06
    循
    0.06
    åĨį
    0.06
    Ñĥда
    0.06
     enfin
    0.06
    Activations Density 0.225%

    No Known Activations