© 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. 21897
    Prev
    Next
    INDEX
    Explanations

    special characters and code snippets

    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
    ua
    -0.06
    ore
    -0.06
    aka
    -0.06
    termin
    -0.06
    ora
    -0.06
    emaker
    -0.06
    erez
    -0.06
    éĤĦåı¯ä»¥
    -0.06
    eration
    -0.06
    æĪijè¿ĺ
    -0.06
    POSITIVE LOGITS
    "group
    0.08
    idge
    0.08
    clave
    0.08
    oport
    0.08
    ivière
    0.08
    âĢ¦]
    0.07
    ANIA
    0.07
    åħ¨éĥ¨è¯Ħ论
    0.07
    oggler
    0.07
    Invoker
    0.07
    Activations Density 0.002%

    No Known Activations