© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49022
    Prev
    Next
    INDEX
    Explanations

    influence and connections

    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
    对人类
    -0.07
    責
    -0.07
     stimulated
    -0.07
    èĩ¼
    -0.06
    诧
    -0.06
    ocup
    -0.06
    为æ¶Īè´¹èĢħ
    -0.06
     certific
    -0.06
    æľīè´£
    -0.06
     destruct
    -0.06
    POSITIVE LOGITS
    å½±åĵįåĬĽ
    0.12
     influence
    0.11
     Influence
    0.11
    çļĦå½±åĵįåĬĽ
    0.10
    å½±åĵįåĬĽçļĦ
    0.10
    çĸıéĢļ
    0.10
    ç§ĺå¯Ĩ
    0.10
     influential
    0.10
    influence
    0.10
     influencing
    0.10
    Activations Density 0.108%

    No Known Activations