© 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. 17593
    Prev
    Next
    INDEX
    Explanations

    losses vs wins

    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
    kait
    -0.08
    à¹Ģà¸Ķ
    -0.07
    ailer
    -0.07
    åĽŃè·¯
    -0.07
    peg
    -0.07
    inux
    -0.07
    éŨå¸Ĥ
    -0.06
    /gcc
    -0.06
    åĴĮçĻ½
    -0.06
    ummer
    -0.06
    POSITIVE LOGITS
     net
    0.13
    åĩĢ
    0.12
    失衡
    0.11
     predomin
    0.11
     imbalance
    0.10
    ä¸į平衡
    0.10
    (net
    0.10
    çĽĪä½Ļ
    0.10
    net
    0.09
     surplus
    0.09
    Activations Density 0.104%

    No Known Activations