© 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. 55992
    Prev
    Next
    INDEX
    Explanations

    `come`, `come`

    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
     ÐĺÑĤак
    -0.08
    hoa
    -0.08
    ...
    -0.08
    actually
    -0.08
     actually
    -0.08
    æīĢ以
    -0.08
    å®ŀéĻħä¸Ĭæĺ¯
    -0.07
    åİĭ
    -0.07
    ......
    -0.07
     say
    -0.07
    POSITIVE LOGITS
    èĢĮåħ¶
    0.10
    å®ĥéĤ£
    0.08
    å®ĥä¸įä»ħ
    0.08
    å®ĥåľ¨
    0.08
    ä¸įçĪ½
    0.07
    lify
    0.07
    å®ĥä»¬åľ¨
    0.07
    å®ĥ以
    0.07
    åīįèĢħ
    0.07
    åľ¨å®ĥ
    0.07
    Activations Density 0.023%

    No Known Activations