© 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. 43243
    Prev
    Next
    INDEX
    Explanations

    actions and their consequences

    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
    anson
    -0.06
    íĿ¬
    -0.06
    åľ¨çĶ¨
    -0.06
    ogs
    -0.06
    PrototypeOf
    -0.06
    å®ŀçī©
    -0.06
    elsey
    -0.05
    åĮĸ为
    -0.05
    濯
    -0.05
    å°ıç¼ĸ
    -0.05
    POSITIVE LOGITS
    è¿ĩæĹ¥åŃIJ
    0.09
    ils
    0.08
    èĢĮæĺ¯åľ¨
    0.08
     ostensibly
    0.08
    约车
    0.08
     обойÑĤиÑģÑĮ
    0.08
    åıĸèĢĮ代ä¹ĭ
    0.08
     пÑĢеÑģÑĤ
    0.07
     ÑıкобÑĭ
    0.07
    çļĦåħ¨éĥ¨åĨħ容
    0.07
    Activations Density 0.539%

    No Known Activations