© 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. 18994
    Prev
    Next
    INDEX
    Explanations

    methods and techniques

    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
    å°±æĺ¯è¿Ļä¹Ī
    -0.07
    jo
    -0.06
    ढ़
    -0.06
    ixo
    -0.06
    ä¸įå°½
    -0.06
     parfois
    -0.06
     fama
    -0.06
     fun
    -0.06
    èĤ²
    -0.06
    çŃīå¤ļ
    -0.06
    POSITIVE LOGITS
     somehow
    0.12
     somewhere
    0.11
    èĥ½å¤Łå°Ĩ
    0.09
     preferably
    0.09
    èĥ½å¤Łåľ¨
    0.09
    èĥ½å¤Łè®©
    0.09
     möglichst
    0.09
    æīįè¡Į
    0.08
    ä»Ģä¹Īä¸ľè¥¿
    0.08
     somew
    0.08
    Activations Density 0.347%

    No Known Activations