© 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. 24079
    Prev
    Next
    INDEX
    Explanations

    unnecessary or invalid

    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
     limited
    -0.09
    éĻIJäºİ
    -0.09
     Limited
    -0.08
    hoff
    -0.08
    åģļä¸įåĪ°
    -0.08
    ä¸į足çļĦ
    -0.08
    _each
    -0.08
    æĹłèĥ½ä¸ºåĬĽ
    -0.08
    失败äºĨ
    -0.07
     impar
    -0.07
    POSITIVE LOGITS
    没æľīå¿ħè¦ģ
    0.13
    没å¿ħè¦ģ
    0.12
    ä¸įéľĢè¦ģ
    0.11
    并ä¸įéľĢè¦ģ
    0.11
    å¤ļä½ĻçļĦ
    0.11
     êµ³
    0.11
    浪费äºĨ
    0.11
    å¤ļä½Ļ
    0.10
     unnecessary
    0.10
    浪费
    0.10
    Activations Density 0.218%

    No Known Activations