© 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. 23384
    Prev
    Next
    INDEX
    Explanations

    ’s ... is

    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
    åį³åĪ°
    -0.09
    æĪijçļĦ书æŀ¶
    -0.09
    æĶ¶äºİ
    -0.08
    建议éĢīæĭ©
    -0.08
    ãĤĴ使çĶ¨ãģĹãģŁ
    -0.08
    à¸Ķัà¸ĩà¸ģลà¹Īาว
    -0.08
    è¿Ļä¸ĢéĹ®é¢ĺ
    -0.07
    æŃ¤ä¸º
    -0.07
    å°ĨæĪij
    -0.07
    asser
    -0.07
    POSITIVE LOGITS
     freaking
    0.09
     handy
    0.09
    æĢİä¹ĪçĶ¨
    0.09
     honestly
    0.08
     goodies
    0.08
     kinda
    0.08
     tell
    0.08
     remember
    0.08
     tells
    0.08
    å°±åĥı
    0.08
    Activations Density 0.017%

    No Known Activations