© 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. 41017
    Prev
    Next
    INDEX
    Explanations

    births and deaths

    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
    è°ļ
    -0.07
    æİ°
    -0.07
    ©
    -0.06
    çµķ
    -0.06
    æ··åIJĪåŀĭ
    -0.06
    igna
    -0.06
    äºļ
    -0.06
    Ĩ
    -0.06
    urate
    -0.06
    mh
    -0.06
    POSITIVE LOGITS
    æ¶ĪçģŃ
    0.08
    è¿Ļä¸ĸä¸Ĭ
    0.08
    çŁ¥è§ī
    0.08
    ikli
    0.07
    èĻļ空
    0.07
    irth
    0.07
    çķĮéĻIJ
    0.07
    å¤Ħéķ¿
    0.07
    èįIJ
    0.07
    dest
    0.07
    Activations Density 0.008%

    No Known Activations