© 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. 42456
    Prev
    Next
    INDEX
    Explanations

    medical advice and professionals

    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
     subcontract
    -0.08
    ong
    -0.08
    asin
    -0.08
     Limo
    -0.08
    rose
    -0.08
    onge
    -0.07
    .googleapis
    -0.07
    volgens
    -0.07
    èĩªç¤¾
    -0.07
     пÑĢоÑģмоÑĤÑĢов
    -0.07
    POSITIVE LOGITS
    æŃ£è§Ħ
    0.07
    åĮ»çĶŁæĮĩ导ä¸ĭ
    0.07
    æŃ£éģĵ
    0.07
    æŃ£è§ĦçļĦ
    0.07
     fitting
    0.07
    åĬĪ
    0.06
     diagnosis
    0.06
     proper
    0.06
     ìĿĺ
    0.06
     diagnose
    0.06
    Activations Density 0.053%

    No Known Activations