© 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. 61014
    Prev
    Next
    INDEX
    Explanations

    able to perform a task

    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
    .mk
    -0.07
    é£ŁãģĦ
    -0.07
    ewire
    -0.07
    elly
    -0.07
     translates
    -0.06
    ynth
    -0.06
    çŁ¥çļĦ
    -0.06
    è¿Ļä¹Ł
    -0.06
    åijĪ
    -0.06
    æĭĩæĮĩ
    -0.06
    POSITIVE LOGITS
     overall
    0.09
     пÑĢедÑĭ
    0.09
     prelimin
    0.08
     superficial
    0.08
    åŁºæľ¬ä¿¡æģ¯
    0.08
     preliminary
    0.08
     Overall
    0.08
     preliminar
    0.08
    åĪĿæŃ¥
    0.08
     already
    0.08
    Activations Density 0.685%

    No Known Activations