© 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. 30866
    Prev
    Next
    INDEX
    Explanations

    all, this, just

    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
    好象
    -0.07
    ablish
    -0.07
    aire
    -0.07
    ä¹ŁåĪ«
    -0.07
    åĦ¿
    -0.07
    ืà¸Ń
    -0.07
    åħ·ä½ĵæĥħåĨµ
    -0.07
    æĿİè½»
    -0.06
     prov
    -0.06
    马æĸ¯
    -0.06
    POSITIVE LOGITS
    IGNED
    0.08
    OTH
    0.07
    atched
    0.07
    raphe
    0.07
    禺
    0.07
    å¾·åĭĴ
    0.07
    _bh
    0.06
    _bm
    0.06
    ĻĤ
    0.06
    ukkan
    0.06
    Activations Density 0.045%

    No Known Activations