© 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. 16881
    Prev
    Next
    INDEX
    Explanations

    hesitation sounds or filler words

    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
    åĽŀå¸ĸ
    -0.09
    æĸĩåĵ²
    -0.09
    æ°Ķå¾Ĺ
    -0.08
    ÃīT
    -0.08
    ç·»
    -0.08
    微信æī«ä¸Ģæī«
    -0.08
    çī¢çī¢
    -0.08
    heen
    -0.08
    tez
    -0.08
    orda
    -0.08
    POSITIVE LOGITS
    ...
    0.07
    åijĥ
    0.07
    âĢ¦
    0.07
     stutter
    0.07
    ä»Ģä¹Īåij¢
    0.07
    åģ¶
    0.06
     anyways
    0.06
     suffice
    0.06
    st
    0.06
    失
    0.06
    Activations Density 0.045%

    No Known Activations