© 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. 41523
    Prev
    Next
    INDEX
    Explanations

    `@param {String}`

    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
    èĢħä¼ĺåħĪ
    -0.09
    éħİ
    -0.09
    ä¸īå°º
    -0.09
    缸åħ³éĹ®é¢ĺ
    -0.08
    åĬĽæīĢèĥ½åıĬ
    -0.08
    ronic
    -0.07
    为å¸Ī
    -0.07
    æĸ¯ç§ij
    -0.07
    rauch
    -0.07
     há»įa
    -0.07
    POSITIVE LOGITS
    æĽ´è¡£
    0.08
    alp
    0.07
    edin
    0.07
    inom
    0.06
    iniz
    0.06
    als
    0.06
    ymb
    0.06
    ç»ĵå©ļè¯ģ
    0.06
    ç¿»
    0.06
    å¸ĤåľºçĽijçĿ£ç®¡çIJĨ
    0.06
    Activations Density 0.001%

    No Known Activations