© 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. 2465
    Prev
    Next
    INDEX
    Explanations

    in particular

    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
    lator
    -0.08
    пÑĥÑĤ
    -0.08
     ÑģÑĤолÑĮко
    -0.07
    ordo
    -0.07
    êu
    -0.07
    schau
    -0.07
    ={({
    -0.07
    ertino
    -0.07
    éĹ®é¢ĺåĪĨæŀIJ
    -0.07
    eur
    -0.07
    POSITIVE LOGITS
    à¸Ńยà¹Īาà¸ĩยิà¹Īà¸ĩ
    0.09
    ä¸įä¹ı
    0.08
    注æĦıåĪ°
    0.07
    bella
    0.06
    ç¼Ń
    0.06
    å½ĵåħ¶
    0.06
     ÑĦакÑĤа
    0.06
    ä¸įä¼ļåĨį
    0.06
    nable
    0.06
    åı¯ä¹IJ
    0.06
    Activations Density 0.028%

    No Known Activations