© 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. 42312
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    spb
    -0.08
    çıĬ
    -0.07
    å°ijåħĪ
    -0.07
    æīĢ以æīį
    -0.07
    hut
    -0.07
    åı¯ä»¥åĪĨ为
    -0.07
    .TryParse
    -0.07
    voz
    -0.06
    :int
    -0.06
    ×Ļק
    -0.06
    POSITIVE LOGITS
    PAS
    0.07
    reeze
    0.07
    对çĶŁæ´»
    0.07
    对人çļĦ
    0.07
    /epl
    0.06
     Notice
    0.06
    keer
    0.06
    ke
    0.06
     лен
    0.06
    è§ĴèIJ½
    0.06
    Activations Density 0.017%

    No Known Activations