© 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. 23110
    Prev
    Next
    INDEX
    Explanations

    vs

    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
    afen
    -0.09
    æıIJæIJº
    -0.07
    à´²àµĨ
    -0.07
    å°ĨæĪij
    -0.07
    заниÑı
    -0.07
    俺
    -0.07
    éĤĤ
    -0.07
    uz
    -0.07
     terc
    -0.06
    illen
    -0.06
    POSITIVE LOGITS
     vs
    0.09
     VS
    0.07
    Fragment
    0.07
     Vs
    0.07
    VS
    0.07
    çļĦçī¹çĤ¹æĺ¯
    0.07
    vs
    0.07
    对å¸Ĥåľº
    0.06
     counterpart
    0.06
    _vs
    0.06
    Activations Density 0.029%

    No Known Activations