© 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. 14342
    Prev
    Next
    INDEX
    Explanations

    moiety or moieties

    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
    åIJĦé¡¹å·¥ä½ľçļĦ
    -0.10
    åIJĦé¡¹å·¥ä½ľ
    -0.08
    åIJĦé¡¹çĽ®
    -0.08
    kund
    -0.08
    dra
    -0.08
    ipt
    -0.07
    å·²è¢«ç³»ç»Ł
    -0.07
    åIJĦ项
    -0.07
    åIJĦéĥ¨éŨ
    -0.07
    /manual
    -0.07
    POSITIVE LOGITS
     presence
    0.11
     présence
    0.11
    Presence
    0.10
     Presence
    0.09
    ç»ĵæŀĦä¸Ń
    0.09
     presença
    0.09
    presence
    0.09
    Clickable
    0.09
    为å®ĺ
    0.08
     presencia
    0.08
    Activations Density 0.037%

    No Known Activations