© 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. 46407
    Prev
    Next
    INDEX
    Explanations

    mercury, CNT toxic, pyrene, nitrobenzene, solvents, APAP-induced

    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
    usy
    -0.07
    笤
    -0.07
    fone
    -0.07
    åŁ¹èĤ²
    -0.07
     Servi
    -0.07
    .dense
    -0.07
    ñana
    -0.06
     revision
    -0.06
    åŃķèĤ²
    -0.06
    ãĤ¯ãĤ·ãĥ§ãĥ³
    -0.06
    POSITIVE LOGITS
    è¿ĽåĪ°
    0.10
    åĪºæ¿Ģ
    0.09
     ÙĪارد
    0.09
     ÑĢаздÑĢа
    0.09
    çĽ´è¾¾
    0.09
     entering
    0.09
    asted
    0.09
    è¿Ľåħ¥
    0.09
     delivered
    0.09
    容æĺĵå¼ķèµ·
    0.09
    Activations Density 0.573%

    No Known Activations