© 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. 30415
    Prev
    Next
    INDEX
    Explanations

    questions, problems, reality

    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
    æķ´ä½ĵä¸Ĭ
    -0.08
    æķ´ä½ĵ
    -0.08
    æĮº
    -0.08
    è¿ĺæĺ¯æĮº
    -0.07
     Overall
    -0.07
    overall
    -0.07
    ä¹ŁæĮº
    -0.07
     targ
    -0.07
    PRETTY
    -0.07
    Overall
    -0.07
    POSITIVE LOGITS
    akk
    0.08
    .obtain
    0.07
    .Private
    0.07
    ÑĢак
    0.07
    hé
    0.07
    alani
    0.07
    /drivers
    0.07
    !!!
    0.07
    çĤ¹èĩ³
    0.07
    æĪijå°±ä¸į
    0.07
    Activations Density 0.010%

    No Known Activations