© 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. 15719
    Prev
    Next
    INDEX
    Explanations

    any questions please

    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
    èµ·çłģ
    -0.06
    èĩ³å°ij
    -0.06
    è¶³å¤Ł
    -0.06
    itives
    -0.06
    å¤Ħå¤Ħ
    -0.06
    çŁ
    -0.06
    足以
    -0.06
    ìĦ¬
    -0.06
     عاÙĦ
    -0.06
     implicitly
    -0.06
    POSITIVE LOGITS
    è¿Ľä¸ĢæŃ¥æ·±åĮĸ
    0.10
     подÑĢобнее
    0.10
     구체ìłģìĿ¸
    0.10
     further
    0.10
     detailed
    0.10
    è¿Ľä¸ĢæŃ¥ä¼ĺåĮĸ
    0.10
    æĽ´å¤ļåħ³äºİ
    0.10
    åħ·é«Ķ
    0.09
    æĽ´æ·±åħ¥
    0.09
     اÙĦÙħزÙĬد
    0.09
    Activations Density 0.038%

    No Known Activations