© 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. 30170
    Prev
    Next
    INDEX
    Explanations

    disagree, want, true

    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
    annage
    -0.09
    è¾¾æĭī
    -0.09
     negoci
    -0.08
    webkit
    -0.08
    -Semit
    -0.08
    tlement
    -0.08
    zyw
    -0.08
    zig
    -0.08
    çļĻ
    -0.08
    miet
    -0.08
    POSITIVE LOGITS
     thing
    0.08
     particulars
    0.06
    æŁIJ
    0.06
    edel
    0.06
    æŁIJæŁIJ
    0.06
     forthcoming
    0.06
     particular
    0.06
     stuff
    0.06
     circumstances
    0.06
    çļĦéĤ£ä¸ªäºº
    0.06
    Activations Density 0.021%

    No Known Activations