© 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. 50068
    Prev
    Next
    INDEX
    Explanations

    high efficiency and performance

    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
    ä¸įåĸĦ
    -0.09
    è¶Ĭå°ij
    -0.08
    å¾®å¦Ļ
    -0.08
    åĬłéĩį
    -0.07
    åħ±æľī
    -0.07
    lest
    -0.07
    åĬłåī§
    -0.07
    elj
    -0.07
     subtle
    -0.07
     непÑĢавилÑĮ
    -0.07
    POSITIVE LOGITS
     achieved
    0.11
    媲ç¾İ
    0.10
    åı¯ä»¥è¾¾åĪ°
    0.10
     achievable
    0.10
     surpass
    0.09
     comparable
    0.09
    åģļåĪ°äºĨ
    0.09
    æĺ¯çĽ®åīį
    0.09
    èĥ½è¾¾åĪ°
    0.09
    ãĤĴå®Łçı¾
    0.09
    Activations Density 0.356%

    No Known Activations