© 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. 27013
    Prev
    Next
    INDEX
    Explanations

    excessive or overly

    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
    ç¨į
    -0.09
    åłĤåłĤ
    -0.08
    ----------------------------------------------------------------------
    -0.08
    riba
    -0.08
    å½ĵåħ¶
    -0.08
    rios
    -0.08
    GEST
    -0.08
     Molto
    -0.07
    ลัà¸ļ
    -0.07
    åħ¨éĿ¢å»ºæĪIJ
    -0.07
    POSITIVE LOGITS
    ä¾Ŀèµĸ
    0.10
     reliance
    0.10
    éĽĨä¸Ńåľ¨
    0.08
    use
    0.08
    åħ³æ³¨åĴĮ
    0.07
    éĽĨä¸Ńäºİ
    0.07
     reliant
    0.07
    追æ±Ĥ
    0.07
     excessive
    0.07
    ä¾Ŀè³´
    0.07
    Activations Density 0.016%

    No Known Activations