© 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. 30552
    Prev
    Next
    INDEX
    Explanations

    cardiac death, ashwagandha, arachidonic acid

    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
    æīĢ欲è¨Ģ
    -0.07
    sey
    -0.07
    imenta
    -0.07
    é£
    -0.07
    amakan
    -0.07
    reck
    -0.07
    æĬĢ
    -0.07
    äºĨä¸ĭåİ»
    -0.07
    çľ
    -0.06
    éħ¸çĶľèĭ¦è¾£
    -0.06
    POSITIVE LOGITS
    unos
    0.07
    ç¿©
    0.06
    _MB
    0.06
    ibas
    0.06
     веÑī
    0.06
    æĪĸèĢħåħ¶ä»ĸ
    0.06
    æ¢ħæŀĹ
    0.06
     wikipedia
    0.06
    ujian
    0.06
    lash
    0.06
    Activations Density 2.022%

    No Known Activations