© 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. 4440
    Prev
    Next
    INDEX
    Explanations

    domain and scope

    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
     megb
    -0.07
    å¥
    -0.07
     dirig
    -0.07
    æ±°
    -0.07
     newInstance
    -0.07
    æĻļé¤IJ
    -0.07
    æĪĸå°ı
    -0.06
    輩
    -0.06
    åľ°å¤´
    -0.06
     master
    -0.06
    POSITIVE LOGITS
     restrictions
    0.08
    æī©å±ķåĪ°
    0.07
    MESS
    0.07
    åıĹéĻIJ
    0.07
    raj
    0.07
    çļĦéĻIJåĪ¶
    0.07
     Restrictions
    0.07
    restrict
    0.07
    batas
    0.07
    mess
    0.06
    Activations Density 0.007%

    No Known Activations