© 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. 21692
    Prev
    Next
    INDEX
    Explanations

    auxiliary verb or particle

    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
    -NLS
    -0.08
    mtree
    -0.08
    etsk
    -0.08
    ÙĪرش
    -0.08
    retta
    -0.08
    ussed
    -0.07
    ziger
    -0.07
    Leaks
    -0.07
    icut
    -0.07
    _ty
    -0.07
    POSITIVE LOGITS
    çĶ¨æ³ķ
    0.08
     rather
    0.06
    anged
    0.06
    æīĺ
    0.06
    ä¸Ń表示
    0.06
     faci
    0.06
    æĹ¶è¡¨ç¤º
    0.06
     Rather
    0.06
    “
    0.06
    rl
    0.06
    Activations Density 0.006%

    No Known Activations