© 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. 28032
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åĴĮåŁİå¸Ĥ
    -0.07
    äºĪ
    -0.07
    idis
    -0.07
    cope
    -0.06
     medida
    -0.06
    æİĸ
    -0.06
     proxim
    -0.06
    omb
    -0.06
    æ¢ħæŀĹ
    -0.06
    ì©
    -0.06
    POSITIVE LOGITS
    commun
    0.08
    æĥ³ä½ł
    0.08
     berin
    0.08
     Heidel
    0.07
    SEX
    0.07
    å°Ĩä½ł
    0.07
    öhn
    0.07
    nok
    0.07
    çĽ¸ä¿¡ä½ł
    0.07
    teis
    0.07
    Activations Density 0.000%

    No Known Activations