© 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. 30155
    Prev
    Next
    INDEX
    Explanations

    LICENSE or file

    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
    ingly
    -0.09
     {*}
    -0.08
    cribing
    -0.08
    çªŁ
    -0.08
    onto
    -0.08
     академи
    -0.08
    pto
    -0.08
    强åĪ¶æݪæĸ½
    -0.08
    ä¸Ńè§Ħ
    -0.07
    ubah
    -0.07
    POSITIVE LOGITS
    å¥
    0.07
    èī°éļ¾
    0.06
     hoang
    0.06
    é¦ĸåħĪè¦ģ
    0.06
     Sr
    0.06
     Ø£ÙĪÙĦاÙĭ
    0.06
    ly
    0.06
     understanding
    0.06
    áng
    0.06
    é¦ĸåħĪ
    0.06
    Activations Density 0.012%

    No Known Activations