© 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. 50044
    Prev
    Next
    INDEX
    Explanations

    niches and descriptive tags

    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
    /delete
    -0.06
    es
    -0.06
    Ùı
    -0.06
    [(
    -0.06
    æ¬
    -0.06
     eis
    -0.06
    åĨ·åĨ»
    -0.06
     policeman
    -0.05
    /
    -0.05
    åIJĮä¸Ģ
    -0.05
    POSITIVE LOGITS
     Uncategorized
    0.10
    TagName
    0.09
    è·ŁæĪij
    0.09
     Luar
    0.08
    ondag
    0.08
    åħ³æ³¨æĪij
    0.08
    åĩ¯è¿ª
    0.07
    ugu
    0.07
    å¿ħçľĭ
    0.07
    ẹo
    0.07
    Activations Density 0.064%

    No Known Activations