© 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. 47091
    Prev
    Next
    INDEX
    Explanations

    refer to

    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
    äºĨä¸Ģå¥Ĺ
    -0.07
    说ä¸į
    -0.06
    hots
    -0.06
    ñana
    -0.06
    梦幻西游
    -0.06
    mins
    -0.06
     Juve
    -0.06
    æĶ¶èİ·äºĨ
    -0.06
    umas
    -0.06
    aventure
    -0.06
    POSITIVE LOGITS
    æ¯Ķæ¯Ķ
    0.08
    沧海
    0.07
    adar
    0.07
    fet
    0.07
    çĽĬ
    0.07
    BOR
    0.07
    boro
    0.07
    èľĹ
    0.07
    à¸Ļิ
    0.07
    Ñİз
    0.07
    Activations Density 0.001%

    No Known Activations