© 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. 30126
    Prev
    Next
    INDEX
    Explanations

    police officers, school lunch, inserting machines

    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
    ivan
    -0.09
    ackers
    -0.09
    lakukan
    -0.09
    åħį费订éĺħ
    -0.08
    anggap
    -0.08
    accio
    -0.08
     ÐļонÑģÑĥлÑĮÑĤа
    -0.08
    garten
    -0.08
    è¿ŀåIJĮ
    -0.08
    _SHADOW
    -0.08
    POSITIVE LOGITS
    以ä¸ĭæĺ¯å°ıç¼ĸ
    0.07
    ĸ
    0.06
    0.06
    âĢ
    0.06
    åĬĽå£«
    0.06
    ãĢİ
    0.06
    Ķ
    0.06
    __
    0.05
    olated
    0.05
    æ¡IJ
    0.05
    Activations Density 0.238%

    No Known Activations