© 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. 17387
    Prev
    Next
    INDEX
    Explanations

    URLs and schema definitions

    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
    Serialize
    -0.08
    ulon
    -0.07
    åıĬè¦ģæ±Ĥ
    -0.07
    åĻľ
    -0.06
    å¿«
    -0.06
    Ŀ
    -0.06
    alles
    -0.06
    à¸ļà¸Ńà¸Ļ
    -0.06
    声声
    -0.06
    alde
    -0.06
    POSITIVE LOGITS
     appunto
    0.07
    ights
    0.07
    交æµģä¸İåIJĪä½ľ
    0.07
    egar
    0.06
    ק×Ļ
    0.06
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.06
    itele
    0.06
    æ¿Ĵ
    0.06
    ä¹ĭéŃĤ
    0.06
    -doc
    0.06
    Activations Density 0.474%

    No Known Activations