© 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. 11164
    Prev
    Next
    INDEX
    Explanations

    thus, therefore, conclusion indicator

    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
    ouce
    -0.08
    emain
    -0.07
     доÑģ
    -0.07
    æīĢ以就
    -0.07
    æīĢ以ä»ĸ们
    -0.07
    oczy
    -0.07
    noi
    -0.07
    acus
    -0.07
    ä¸Ģç³»åĪĹçļĦ
    -0.07
    ravi
    -0.07
    POSITIVE LOGITS
    ä¸įä»ħèĥ½å¤Ł
    0.08
    è¶Ĭæĺ¯
    0.08
    åį³ä¾¿
    0.07
    ledes
    0.07
    ä¸įä»ħèĥ½
    0.07
    åį³ä¾¿æĺ¯
    0.07
    åį³ä½¿
    0.06
    oba
    0.06
    itled
    0.06
    idan
    0.06
    Activations Density 0.019%

    No Known Activations