© 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. 33095
    Prev
    Next
    INDEX
    Explanations

    reporting speech or statements

    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
    åľ¨æŁIJäºĽ
    -0.07
    éĤ£ä¸ªæŶåĢĻ
    -0.07
    使å®ĥ
    -0.06
    éĤ£ä¸Ģå¹´
    -0.06
    ä¿®çļĦ
    -0.06
    ä»°æľĽ
    -0.06
    idd
    -0.06
    æĺ¯å¾Ī
    -0.06
    åĪĨæķ£
    -0.06
    èIJĥ
    -0.06
    POSITIVE LOGITS
    æĺ¨
    0.10
     edil
    0.08
    osos
    0.08
    éºĴ
    0.08
    agas
    0.07
     íķľíݸ
    0.07
    stitu
    0.07
    ibel
    0.07
    è¯łéĩĬäºĨ
    0.07
    alytics
    0.07
    Activations Density 0.340%

    No Known Activations