© 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. 41490
    Prev
    Next
    INDEX
    Explanations

    molten metal or material

    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
    akas
    -0.09
     AsyncTask
    -0.08
    rella
    -0.08
    缤
    -0.07
    اشت
    -0.07
    tiin
    -0.07
    ì¦ĿìĿĦ
    -0.07
    apas
    -0.07
    è¦
    -0.07
     пÑĢогÑĢеÑģÑģи
    -0.07
    POSITIVE LOGITS
    çĨĶåĮĸ
    0.09
    çļĦé«ĺ温
    0.09
    çĨĶ
    0.09
    åĩĿåĽº
    0.08
    æµģæ·Į
    0.08
    à¹Ħหล
    0.08
    èŀįèŀį
    0.07
    æµģåĬ¨æĢ§
    0.07
    çĨĶèŀį
    0.07
    液æĢģ
    0.07
    Activations Density 0.021%

    No Known Activations