© 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. 58657
    Prev
    Next
    INDEX
    Explanations

    suffixes like 'ers', 'ian', 'ov', 'nel', 'dor'

    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
    å¤ļä¹Ī
    -0.07
    incident
    -0.07
    æĶ¶éĽĨæķ´çIJĨ
    -0.06
    Ø£ÙĥÙħÙĦ
    -0.06
    ÙĪÙħاÙĨ
    -0.06
     atan
    -0.06
    à¸ĭà¹īà¸Ńà¸Ļ
    -0.06
     Mohamm
    -0.06
    É
    -0.06
    蹦蹦
    -0.06
    POSITIVE LOGITS
    oods
    0.07
    ay
    0.07
    太ä»ĵ
    0.07
    åĿIJ
    0.07
    éļľ
    0.07
    mtree
    0.06
     piyas
    0.06
    jec
    0.06
    æ¸ħæŃ£
    0.06
    lete
    0.06
    Activations Density 0.020%

    No Known Activations