© 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. 33572
    Prev
    Next
    INDEX
    Explanations

    continuous flow

    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
    akh
    -0.07
     glare
    -0.06
    å·¥åħ·ç®±
    -0.06
    ç»ijæīİ
    -0.06
     emanc
    -0.06
    ä¸įèĥ½åĨį
    -0.06
    ģ
    -0.06
    Jump
    -0.06
    çĶ¨åĬĽ
    -0.06
    éŨçļĦ
    -0.06
    POSITIVE LOGITS
     flow
    0.14
    æµģéĢŁ
    0.13
    flow
    0.13
     Flow
    0.12
    Flow
    0.12
    -flow
    0.12
     flows
    0.12
    .flow
    0.11
    _flow
    0.11
     поÑĤок
    0.11
    Activations Density 0.115%

    No Known Activations