© 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. 29899
    Prev
    Next
    INDEX
    Explanations

    dates like YYYY-MM-DD

    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
    /native
    -0.08
     conserv
    -0.08
    ardino
    -0.08
    akai
    -0.07
    羣æĬĵå®ŀå¹²
    -0.07
    rika
    -0.07
    åŁ¼
    -0.07
    å°Ķå¤ļ
    -0.07
    AuthToken
    -0.07
    #from
    -0.07
    POSITIVE LOGITS
    群ä¼Ĺ
    0.07
     aux
    0.07
    åĩĨ
    0.06
    azo
    0.06
    æķĪ
    0.06
     dep
    0.06
    森æŀĹ
    0.06
    æĺ¯åħ¨
    0.06
    qed
    0.06
    éĤ®
    0.06
    Activations Density 0.062%

    No Known Activations