© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 62576
    Prev
    Next
    INDEX
    Explanations

    actions or states

    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
     ê°ĢëĬ¥íķĺë©°
    -0.08
    ä¹ĭæīĢ以
    -0.08
    ãģįãģ¾ãģĹãģŁãģĮ
    -0.07
    ÙĦز
    -0.07
    åIJĹ
    -0.07
    åĽłæŃ¤åľ¨
    -0.07
     jopa
    -0.07
     whoever
    -0.07
     zwar
    -0.07
     donc
    -0.06
    POSITIVE LOGITS
    à¸ģà¹ĩà¸ķาม
    0.11
     sekalipun
    0.09
    }):
    0.09
    )):
    0.09
    )?.
    0.09
    "):
    0.08
    ")).
    0.08
    )).
    0.08
    ï½ŀãĢĤ
    0.08
    çļĦç¼ĺæķħ
    0.08
    Activations Density 1.149%

    No Known Activations