© 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. 7568
    Prev
    Next
    INDEX
    Explanations

    citations like [@B1]

    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
    á»ĵng
    -0.07
    еÑģÑĤа
    -0.06
    éĢ
    -0.06
    çŃĭ骨
    -0.06
    çĻ¾æĹ¥
    -0.06
    zek
    -0.06
    -ra
    -0.06
    ilta
    -0.06
    åºľ
    -0.06
    大约æľī
    -0.06
    POSITIVE LOGITS
    Ahead
    0.08
     Prosp
    0.07
    otropic
    0.07
    ä¸ļåĬ¡æ°´å¹³
    0.07
    á»ĩp
    0.07
    หม
    0.07
    æłĢ
    0.06
    æ¶Ī
    0.06
    èĮĥåĦ¿
    0.06
    ÃģT
    0.06
    Activations Density 0.304%

    No Known Activations