© 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. 51813
    Prev
    Next
    INDEX
    Explanations

    this is followed by question

    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¦ĥ
    -0.08
     ÑıкобÑĭ
    -0.08
    èĮ«èĮ«
    -0.08
    好å¤Ħ
    -0.08
    ogle
    -0.08
    chos
    -0.08
    eref
    -0.08
    achines
    -0.08
    ÑĦон
    -0.08
    ersist
    -0.08
    POSITIVE LOGITS
    äºĨä¸įå°ij
    0.07
    åıĪæĺ¯ä¸Ģ个
    0.06
     Man
    0.06
    __()
    0.06
    ç»Īäºİ
    0.06
    juan
    0.06
    è¿Ļ个éĹ®é¢ĺ
    0.06
    çIJ¢ç£¨
    0.06
    æ£ĺ
    0.06
    äºĨåķĬ
    0.06
    Activations Density 0.008%

    No Known Activations