© 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. 55425
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
    æĥħåĨµåĪĨæŀIJ
    -0.07
    vet
    -0.06
    alt
    -0.06
     Nol
    -0.06
    åħ¶å®ĥçļĦ
    -0.06
    æĮīçħ§åĽ½å®¶
    -0.06
    åĵ¥çļĦ
    -0.06
    彦
    -0.06
    èĭ«
    -0.06
    POSITIVE LOGITS
    çĻ½éľ²
    0.08
    hov
    0.08
    puis
    0.07
    adang
    0.07
     Unblock
    0.07
    ãĤĴãģ¯ãģĺãĤģ
    0.07
    ãĥ³ãĤ°
    0.07
    ãĢįãĢģãĢĮ
    0.07
    ãĢįãĢĮ
    0.07
    _finder
    0.07
    Activations Density 0.139%

    No Known Activations