© 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. 62600
    Prev
    Next
    INDEX
    Explanations

    javascript code blocks

    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
     replic
    -0.06
    åݦ
    -0.06
    bare
    -0.06
    è½»åŀĭ
    -0.06
    æīĢè°ĵçļĦ
    -0.06
    åŁŁ
    -0.06
    tras
    -0.06
    yl
    -0.06
    åĪ°åºŃ
    -0.06
     conform
    -0.06
    POSITIVE LOGITS
    çľĭä¸Ģçľĭ
    0.08
    erche
    0.08
    ÑħÑĢо
    0.08
    atriz
    0.08
    æĺ¯ä¸Ģ大
    0.08
     ës
    0.08
    wald
    0.08
    fach
    0.08
     spokeswoman
    0.07
    éĢĨ天
    0.07
    Activations Density 0.172%

    No Known Activations