© 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. 61953
    Prev
    Next
    INDEX
    Explanations

    expressing needs or requests

    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
    åĩŃ
    -0.08
    igrations
    -0.07
    yles
    -0.07
    ãĤ¤ãĥī
    -0.07
     unp
    -0.07
    ooter
    -0.06
     unpopular
    -0.06
    -www
    -0.06
    quirer
    -0.06
    æĽ´å°ij
    -0.06
    POSITIVE LOGITS
     meticulously
    0.08
    _requirements
    0.07
    ymar
    0.07
    åħ¸
    0.07
    满å¿ĥ
    0.07
     Potre
    0.07
    åıĬè¦ģæ±Ĥ
    0.07
    arik
    0.07
    è¿ĻäºĽæķ°æį®
    0.07
    å¸ĮæľĽå¯¹
    0.07
    Activations Density 0.006%

    No Known Activations