© 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. 29801
    Prev
    Next
    INDEX
    Explanations

    positive and negative areas

    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
    æ³½æ°ij
    -0.07
    Leaks
    -0.07
    太快
    -0.07
    éĢŁçİĩ
    -0.07
    åľ¨è´Ńä¹°
    -0.07
    riet
    -0.06
     hast
    -0.06
     Rapids
    -0.06
    Crypt
    -0.06
    stime
    -0.06
    POSITIVE LOGITS
    -positive
    0.10
     positive
    0.09
     Positive
    0.09
    -negative
    0.09
     positives
    0.08
    Positive
    0.08
    çĽĪ
    0.08
     Negative
    0.08
     negative
    0.08
    _positive
    0.08
    Activations Density 0.005%

    No Known Activations