© 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. 10136
    Prev
    Next
    INDEX
    Explanations

    states and outcomes

    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
    æĻĤéĸĵåħ§
    -0.09
    amble
    -0.09
     ÙĪاÙĦÙħت
    -0.08
    yaj
    -0.08
     thá»īnh
    -0.08
    ä¸įæĸŃæİ¨è¿Ľ
    -0.08
    æŶéĹ´åĨħ
    -0.08
    æĹ¥çĶŁ
    -0.08
    akah
    -0.08
    å¹´åįĬ
    -0.08
    POSITIVE LOGITS
    并使
    0.08
    使ä¹ĭ
    0.08
     thereby
    0.08
     пÑĥÑĤем
    0.08
    è¿ĽèĢĮ
    0.08
     temporarily
    0.07
     indefinitely
    0.07
     via
    0.06
     disproportionately
    0.06
    renz
    0.06
    Activations Density 0.276%

    No Known Activations