© 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. 61298
    Prev
    Next
    INDEX
    Explanations

    abbreviations followed by parenthesis

    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
    ":["
    -0.07
     -
    -0.06
    æIJŀå¾Ĺ
    -0.06
    éĥİ
    -0.06
     inve
    -0.06
    bli
    -0.06
    Ĺ
    -0.06
    itti
    -0.06
    迸
    -0.06
     oppos
    -0.06
    POSITIVE LOGITS
    æĺ¯äººä½ĵ
    0.08
    Vectorizer
    0.08
    acan
    0.07
    äk
    0.07
    çĶ³è¯·èģĮä½į
    0.07
    lice
    0.07
    jsc
    0.07
    æĺ¯ä¸Ģå¹´
    0.07
    swith
    0.07
    pj
    0.07
    Activations Density 0.504%

    No Known Activations