© 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. 13566
    Prev
    Next
    INDEX
    Explanations

    reports or statements by names

    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
    AML
    -0.07
    æĪĸå¤ļæĪĸå°ij
    -0.07
    orst
    -0.07
    å¤ļå°ij次
    -0.06
    åħ³æ³¨æĪij们
    -0.06
    -cookie
    -0.06
    大湾åĮº
    -0.06
    ButtonText
    -0.06
    cod
    -0.06
    说ä¸įå®ļ
    -0.06
    POSITIVE LOGITS
    认为
    0.09
     justified
    0.08
    认为æĺ¯
    0.08
    ä»ĸ们认为
    0.08
    çIJĨçĶ±æĺ¯
    0.08
    ä¸ĵ家认为
    0.08
    è¾¾æĪIJçļĦ
    0.08
    认å®ļçļĦ
    0.08
    æĪijä»¬çĽ¸ä¿¡
    0.08
    nty
    0.07
    Activations Density 0.149%

    No Known Activations