© 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. 39747
    Prev
    Next
    INDEX
    Explanations

    _SC_COLL_WEIGHTS_MAX path

    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
    MP
    -0.07
    æıIJ
    -0.07
    é
    -0.07
    容
    -0.07
    é¦ĸåħĪ
    -0.06
    æ²Ļæ²³
    -0.06
    mp
    -0.06
    åī
    -0.06
    åĪĨ
    -0.06
    æĸ½
    -0.06
    POSITIVE LOGITS
    快讯
    0.08
    缸åħ³èµĦ讯
    0.08
    缸åħ³éĹ®çŃĶ
    0.08
    å¤ĩå¿ĺ
    0.08
    ếm
    0.08
    estia
    0.08
    _PS
    0.08
    Ñĺе
    0.08
    appoint
    0.07
    ifax
    0.07
    Activations Density 0.033%

    No Known Activations