© 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. 17337
    Prev
    Next
    INDEX
    Explanations

    port numbers and fields

    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
     ê²ĥìĿ´ê³ł
    -0.08
     ìķĦëĭĪê³ł
    -0.07
     ì¢ĭê³ł
    -0.07
    ä¸Ģæĸij
    -0.07
    åĮºåĴĮ
    -0.07
    çĤ¹äºĨ
    -0.07
    builder
    -0.07
    íĽĪ
    -0.07
    并å°Ĩ
    -0.06
    èĢĮè¿Ļç§į
    -0.06
    POSITIVE LOGITS
    éĤ£ä¹Īä½ł
    0.08
    éĤ£ä¹Ī
    0.08
    éĤ£ä¹Īè¿Ļ个
    0.07
    åĪĻ该
    0.07
    CKET
    0.07
    kking
    0.07
     Inizi
    0.07
    ")==
    0.07
    ahnya
    0.07
    zzo
    0.07
    Activations Density 0.039%

    No Known Activations