© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9601
    Prev
    Next
    INDEX
    Explanations

    functions, constant, toxic, work, pay, fun, aids, cure, bind, represented

    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
     infatti
    -0.12
    à¸Ĺีà¹Īà¹Ģà¸Ľà¹ĩà¸Ļ
    -0.09
    æīĢ
    -0.09
    à¸Ĺีà¹Īà¹Ģà¸ģิà¸Ķ
    -0.09
     γεγονÏĮÏĤ
    -0.08
     olyan
    -0.08
     имеÑı
    -0.08
    à¸Ĺีà¹Īà¹Ģà¸ģิà¸Ķà¸Ĥึà¹īà¸Ļ
    -0.08
    à¸Ĺีà¹Īà¹Ħà¸Ķà¹ī
    -0.08
     pois
    -0.08
    POSITIVE LOGITS
     appunto
    0.11
     بدÙĪرÙĩ
    0.08
    åį´åıĪ
    0.08
    åį´æĹłæ³ķ
    0.08
     otherwise
    0.07
    /></
    0.07
     magari
    0.07
    é¹Ń
    0.07
     pourtant
    0.07
    راز
    0.07
    Activations Density 1.249%

    No Known Activations