© 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. 47355
    Prev
    Next
    INDEX
    Explanations

    answers in lists

    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
    足以
    -0.07
    ãĥ«ãĥĪ
    -0.07
    æĺ¯ä¸įå¤ŁçļĦ
    -0.07
    éĢıå½»
    -0.07
    ttore
    -0.07
    åŁł
    -0.07
     hinaus
    -0.07
    ×Ļ×ĵ
    -0.07
    пÑĸ
    -0.07
    hasOne
    -0.06
    POSITIVE LOGITS
    ç«ŁçĦ¶æĺ¯
    0.08
    ç«ŁçĦ¶
    0.08
    å±ħçĦ¶
    0.08
     ÑıкобÑĭ
    0.08
    ours
    0.08
    arti
    0.07
     prescribed
    0.07
    ÃŃns
    0.06
    åĭĺ
    0.06
     anomal
    0.06
    Activations Density 0.007%

    No Known Activations