© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14386
    Prev
    Next
    INDEX
    Explanations

    independently controlled

    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
    æĿ¥çļĦæŶåĢĻ
    -0.08
    uropa
    -0.07
    çļĦæľīæķĪæĢ§
    -0.07
    æķĻèĤ²æĺ¯
    -0.07
    å°ıçļĦæŶåĢĻ
    -0.07
    opia
    -0.07
    æľĢæł¹æľ¬
    -0.07
    plication
    -0.07
    纨ç»Ķ
    -0.06
    以ä¸ĭ为
    -0.06
    POSITIVE LOGITS
    åĪĽæĸ°åŀĭ
    0.07
     differently
    0.07
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.07
    mier
    0.07
    ãģĿãģĨãģª
    0.07
    ersp
    0.07
    ;}
    0.07
    errated
    0.07
    æĿijæĿijæ°ij
    0.07
    igate
    0.06
    Activations Density 1.094%

    No Known Activations