© 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. 62521
    Prev
    Next
    INDEX
    Explanations

    described as

    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
    itys
    -0.07
    äºĨä½ł
    -0.07
    olt
    -0.07
    ulle
    -0.07
    ity
    -0.07
    å°±åľ°
    -0.06
    äºĨä»ĸ们
    -0.06
    lest
    -0.06
    åĪĽæĦı设计
    -0.06
    kel
    -0.06
    POSITIVE LOGITS
     sebagai
    0.18
    ä½ľä¸º
    0.14
    å½ĵä½ľ
    0.14
    ä½ľä¸ºä¸Ģ个
    0.14
    çķ¶ä½ľ
    0.13
     jako
    0.13
     ÏīÏĤ
    0.13
    ä½ľçĤº
    0.13
    çľĭä½ľ
    0.13
    ä½ľä¸ºä¸Ģç§į
    0.12
    Activations Density 0.304%

    No Known Activations