© 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. 42453
    Prev
    Next
    INDEX
    Explanations

    relationship, inheritance, hierarchy, order

    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
    ç¹Ķ
    -0.08
    éĩİ
    -0.07
    ç»ĩ
    -0.07
    ÙĪدÙĩ
    -0.07
    orro
    -0.07
    usty
    -0.07
    umph
    -0.06
    "sync
    -0.06
    çļĦä»ĸ
    -0.06
    ä¸ŃèģĶ
    -0.06
    POSITIVE LOGITS
    åħ³ç³»
    0.12
    åħ³ç³»ä¸Ń
    0.12
     relationship
    0.11
    åħ³ç³»çļĦ
    0.11
     relations
    0.10
     relationships
    0.10
     hierarchy
    0.10
     relation
    0.10
    _relationship
    0.09
    éĹľä¿Ĥ
    0.09
    Activations Density 0.032%

    No Known Activations