© 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. 29215
    Prev
    Next
    INDEX
    Explanations

    first record

    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
    angan
    -0.07
    âĢ
    -0.06
    人æ°ijçĶŁæ´»
    -0.06
    Âł
    -0.06
    çĭŀ
    -0.06
     Gol
    -0.06
     bewer
    -0.05
     rum
    -0.05
    avel
    -0.05
    è¿«
    -0.05
    POSITIVE LOGITS
    åŃĺ
    0.09
    纪åħĥ
    0.08
    ãģ¾ãĤĵ
    0.08
    à¸ĺ
    0.08
    æŁIJä¸Ģ个
    0.08
    åde
    0.08
    onus
    0.08
    å¼Ģå±ķ好
    0.08
     hüb
    0.07
    onale
    0.07
    Activations Density 0.024%

    No Known Activations