© 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. 42279
    Prev
    Next
    INDEX
    Explanations

    comparison to

    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
    æī«çłģåħ³æ³¨
    -0.08
    adia
    -0.08
    ä¸İ被
    -0.07
    注åĨĮèµĦéĩij
    -0.07
    ieste
    -0.06
    ascus
    -0.06
    anÃŃ
    -0.06
    åŃIJæĽ°
    -0.06
    å¼ĢéĻ¤
    -0.06
    zyd
    -0.06
    POSITIVE LOGITS
    åħ¶ä»ĸåľ°æĸ¹
    0.08
     anderer
    0.08
    对åħ¶è¿Ľè¡Į
    0.08
    æĬĬå®ĥ
    0.07
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.07
    åľ¨åħ¶ä»ĸ
    0.07
    åħ¶å®ĥ
    0.07
     similarly
    0.07
     spots
    0.07
    åħ¶ä»ĸ
    0.07
    Activations Density 0.548%

    No Known Activations