© 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. 17416
    Prev
    Next
    INDEX
    Explanations

    factors influencing or affecting

    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
    andai
    -0.09
    çŃīçī¹èī²
    -0.09
    ÑĨеле
    -0.09
    åİŁä½ĵ
    -0.08
    缮çļĦçļĦ
    -0.08
    ,proto
    -0.08
    ĥĿ
    -0.08
    hpp
    -0.08
    FLAG
    -0.08
    ä¸įä¼ļåĩºçİ°
    -0.08
    POSITIVE LOGITS
     factors
    0.20
    è¿ĻäºĽåĽłç´ł
    0.19
    åĽłç´ł
    0.18
     Factors
    0.17
    çļĦåĽłç´ł
    0.16
    å½±åĵįåĽłç´ł
    0.16
    åĽłç´łçļĦ
    0.16
     influencing
    0.15
     influences
    0.15
    åĽłç´łçļĦå½±åĵį
    0.15
    Activations Density 0.106%

    No Known Activations