© 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. 30346
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming symbols

    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
    áĥĺáĥł
    -0.07
    åĪĩå®ŀå¢ŀ强
    -0.07
    çģ¿
    -0.06
    otto
    -0.06
    ä¸įèĥ½åĨį
    -0.06
    ame
    -0.06
    оÑģÑĤо
    -0.06
    æ¯ıçıŃ
    -0.06
    ibel
    -0.06
     /^(
    -0.05
    POSITIVE LOGITS
    碧çİī
    0.08
    erot
    0.08
    XMLElement
    0.08
    atsu
    0.07
    parator
    0.07
    åıĸãĤĬ
    0.07
    emplates
    0.07
    ekar
    0.07
    osg
    0.07
    eté
    0.07
    Activations Density 0.003%

    No Known Activations