© 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. 33336
    Prev
    Next
    INDEX
    Explanations

    only afterwards

    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
    ENAME
    -0.09
    STS
    -0.08
    ä½łæĺ¯ä¸Ģ个
    -0.08
    ormais
    -0.08
    aksi
    -0.08
    ENU
    -0.08
     pornografia
    -0.08
    estina
    -0.08
    itul
    -0.08
    å°Ķåħĭ
    -0.08
    POSITIVE LOGITS
    æĦıå¤ĸçļĦ
    0.06
    âĢ¢
    0.06
    çĦ¶åIJİæł¹æį®
    0.06
    å¾½
    0.06
    Âł
    0.06
    uz
    0.06
    æ¸ħæ¸ħ
    0.06
    |
    0.06
    æĦıå¤ĸ
    0.06
    ä¸įäºĮ
    0.06
    Activations Density 0.002%

    No Known Activations