© 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. 27613
    Prev
    Next
    INDEX
    Explanations

    inequalities and equality

    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
    å°¼äºļ
    -0.10
    ä½Ĩä¸įéĻIJäºİ
    -0.10
    åĬłæĭ¿å¤§
    -0.09
    ivate
    -0.08
    iin
    -0.08
    _DEFINED
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    ä¼ĹæīĢåij¨çŁ¥
    -0.08
    edException
    -0.08
    iaga
    -0.08
    POSITIVE LOGITS
    ities
    0.07
    -free
    0.07
    eft
    0.07
    á»ģm
    0.07
    dades
    0.06
    Ùģاء
    0.06
     involving
    0.06
    oft
    0.06
    eous
    0.06
    SSERT
    0.06
    Activations Density 0.015%

    No Known Activations