© 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. 11276
    Prev
    Next
    INDEX
    Explanations

    deficiencies and belongs

    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
    æīĢéľĢçļĦ
    -0.08
     consisted
    -0.07
    åĽ
    -0.07
    æīĢéľĢ
    -0.07
     achievable
    -0.07
    å®Įåħ¨
    -0.07
    以示
    -0.06
    éľĢè¦ģçļĦ
    -0.06
    éľĢè¦ģçĶ¨
    -0.06
    æĦıåij³çĿĢ
    -0.06
    POSITIVE LOGITS
    å¹¿æ³ĽçĶ¨äºİ
    0.11
    å¹¿æ³ĽçļĦ
    0.10
     involvement
    0.09
    çļĦä½ľçĶ¨æĺ¯
    0.09
    主è¦ģçĶ¨äºİ
    0.09
    å¹¿æ³ĽçļĦåºĶçĶ¨
    0.09
    被èªī为
    0.09
    强æĤį
    0.09
    å¹¿æ³ĽåºĶçĶ¨äºİ
    0.09
    éĩįè¦ģçļĦä½ľçĶ¨
    0.09
    Activations Density 0.285%

    No Known Activations