© 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. 2862
    Prev
    Next
    INDEX
    Explanations

    fractions or numbers with 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
    sher
    -0.09
    çĻ¾å·Ŀ
    -0.09
    ÙģÙĬÙĨ
    -0.08
    lav
    -0.08
    rimi
    -0.08
    æ²³éķĩ
    -0.08
    emma
    -0.08
    ISMO
    -0.08
    ëĭī
    -0.08
     tremend
    -0.07
    POSITIVE LOGITS
    ä¹³
    0.07
     neut
    0.07
     neither
    0.07
    äl
    0.06
    ãĥ£
    0.06
    æĢ¨
    0.06
     cycle
    0.06
    ERV
    0.06
     asn
    0.06
    ãģĦãģļãĤĮ
    0.06
    Activations Density 0.001%

    No Known Activations