© 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. 65287
    Prev
    Next
    INDEX
    Explanations

    detector circuit or separator

    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
    æģ¯
    -0.07
    zol
    -0.07
    ä¸įæĭĶ
    -0.07
    umpt
    -0.07
    ä¸ĢæľĿ
    -0.06
    ç»ĻåĪ«äºº
    -0.06
    缮æłĩä»»åĬ¡
    -0.06
    éļħ
    -0.06
    çĽĪçĽĪ
    -0.06
    æģ¯çļĦ
    -0.06
    POSITIVE LOGITS
    yac
    0.09
     seguido
    0.09
     followed
    0.09
    ãĤĴçµĮãģ¦
    0.08
    çĦ¶åIJİæĺ¯
    0.08
    çݯèĬĤä¸Ń
    0.08
    è¿ĻéĩĮæĺ¯
    0.08
    çŃīçݯèĬĤ
    0.08
    ä¹ĭåIJİçļĦ
    0.08
    oller
    0.08
    Activations Density 0.125%

    No Known Activations