© 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. 8809
    Prev
    Next
    INDEX
    Explanations

    buffer overflow

    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
     ÎŃγι
    -0.08
    æł·æł·
    -0.08
    æĸ°åħī
    -0.08
    åºŁæŃ¢
    -0.08
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.08
    æĢ§åĬŁèĥ½
    -0.08
    ontos
    -0.08
     âĢ¦.
    -0.08
    ãģªãģĹ
    -0.08
    ayat
    -0.07
    POSITIVE LOGITS
     vs
    0.08
     ONLY
    0.07
    çŃĸçķ¥
    0.06
    '''
    0.06
    S
    0.06
    gin
    0.06
     fucking
    0.06
    rovers
    0.06
    ↵        ↵
    0.06
    ÑĦелÑĮ
    0.06
    Activations Density 0.002%

    No Known Activations