© 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. 39126
    Prev
    Next
    INDEX
    Explanations

    Love & Hip Hop

    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
    ì§Ģ를
    -0.06
     downright
    -0.06
    -0.06
    ize
    -0.05
    åĬłæĭ¿å¤§
    -0.05
    se
    -0.05
    еÑģе
    -0.05
    tsiz
    -0.05
    æľī人
    -0.05
    ÑģÑģе
    -0.05
    POSITIVE LOGITS
    ฯ
    0.09
    ovsky
    0.09
    0.08
    intang
    0.08
    posito
    0.08
    ä»ĭçŁ³
    0.07
    inux
    0.07
    好åij¢
    0.07
    缸åħ³æ³ķå¾ĭ责任
    0.07
    hev
    0.07
    Activations Density 0.463%

    No Known Activations