© 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. 64728
    Prev
    Next
    INDEX
    Explanations

    George 5

    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
     صد
    -0.06
    ä¸Ģä¸ĭå°±
    -0.06
    çħ²
    -0.06
    croft
    -0.06
    asis
    -0.06
    å¾Ĺ人
    -0.06
    æīĴ
    -0.05
    æĴ
    -0.05
    ä¸įæ¯Ķ
    -0.05
    aci
    -0.05
    POSITIVE LOGITS
     ÙĥØ°ÙĦÙĥ
    0.08
     **:**
    0.08
    tru
    0.08
    prit
    0.07
    ëĵľë¦¬
    0.07
    Ñĸд
    0.07
    åĭĩå¾Ģ缴åīį
    0.07
    icho
    0.07
    æĭ¥
    0.07
    arkers
    0.07
    Activations Density 0.058%

    No Known Activations