© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39402
    Prev
    Next
    INDEX
    Explanations

    GNU General Public License version

    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
    åĢºåĪ¸ä¿¡æģ¯
    -0.10
    èī²åĪĹ
    -0.09
    гада
    -0.09
    udas
    -0.08
    ftime
    -0.08
    achable
    -0.08
    isman
    -0.08
    Calibri
    -0.08
    phu
    -0.08
    æĹ¥åĪ¶
    -0.08
    POSITIVE LOGITS
     GNU
    0.07
     appunto
    0.06
    Âł
    0.06
    /LICENSE
    0.06
    åľ¨æ³ķå¾ĭ
    0.06
    0.06
    éĻĦ
    0.06
     liberal
    0.06
    æľŁæ»¡åIJİ
    0.06
    -
    0.06
    Activations Density 1.415%

    No Known Activations