© 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. 3655
    Prev
    Next
    INDEX
    Explanations

    notes, law, past, there, just, as, cut

    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
    edal
    -0.08
    没æľīä¸Ŀ毫
    -0.07
    ене
    -0.07
    æ¯ı天æľī
    -0.07
    ìĹ
    -0.07
    åĨįæİ¥
    -0.07
    schirm
    -0.07
    aiser
    -0.07
    éij«
    -0.07
    oke
    -0.07
    POSITIVE LOGITS
    wah
    0.07
    è®¤çľŁçļĦ
    0.07
     NOP
    0.07
    assis
    0.07
    è¿ĻäºĽéĹ®é¢ĺ
    0.07
    NOP
    0.07
     ìĿ¼ëĭ¨
    0.07
    ãģ¨ãĤĬãģĤãģĪãģļ
    0.07
    åIJĪçIJĨçļĦ
    0.06
    idah
    0.06
    Activations Density 0.016%

    No Known Activations