© 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. 64131
    Prev
    Next
    INDEX
    Explanations

    literary titles and phrases

    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
    å¹´åįİ
    -0.07
    çIJ³å¨ľ
    -0.07
    eneuve
    -0.07
    åĪ¹
    -0.06
    ripper
    -0.06
     pront
    -0.06
    åħµåº«çľĮ
    -0.06
    鸯
    -0.06
    家ä¼Ļ
    -0.06
    天çĽĸ
    -0.06
    POSITIVE LOGITS
    çģ«çĥ§
    0.08
    atsz
    0.07
    aide
    0.07
    第ä¸ĢåIJį
    0.07
     Forbes
    0.07
    çŀ»
    0.07
    atian
    0.07
    缸åħ³è§Ħå®ļ
    0.07
    èĩ´
    0.07
    éĻ·
    0.07
    Activations Density 0.025%

    No Known Activations