© 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. 15375
    Prev
    Next
    INDEX
    Explanations

    subventricular zone, granular zone

    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
    iep
    -0.06
    .baomidou
    -0.06
    åĪĿå§ĭåĮĸ
    -0.06
    دÙĬÙĤ
    -0.06
    å¼Ģå±Ģ
    -0.06
    缸éļĶ
    -0.06
    pend
    -0.06
    åħ¥åѦèĢĥè¯ķ
    -0.06
    å¼Ģåľº
    -0.05
     пеÑĢео
    -0.05
    POSITIVE LOGITS
    åİ»åIJij
    0.13
    éĢģå¾Ģ
    0.13
    è¾ĵåĩºçļĦ
    0.12
    转移åĪ°
    0.12
    转åĮĸæĪIJ
    0.12
    éĶĢå¾Ģ
    0.12
    è¾ĵåĩº
    0.12
    åı¯ä»¥åIJij
    0.11
    éĢļå¾Ģ
    0.11
    åIJijå¤ĸ
    0.11
    Activations Density 0.957%

    No Known Activations