© 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. 64174
    Prev
    Next
    INDEX
    Explanations

    assessment

    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
    emd
    -0.07
    ibble
    -0.07
    èĩªè¨Ģ
    -0.07
    ä¼ģä¸ļåħ³ç³»
    -0.07
    æĮīæľŁ
    -0.07
     wonder
    -0.07
     handleMessage
    -0.07
    è¾īæĺł
    -0.07
    çĥ¨
    -0.07
     setFrame
    -0.07
    POSITIVE LOGITS
    åħħåĪĨäºĨ解
    0.10
    æij¸åºķ
    0.09
     íĮĮìķħ
    0.09
    åĴĮéľĢæ±Ĥ
    0.09
    çŁ¥å·±
    0.09
     ermittelt
    0.09
    对çĹĩä¸ĭèį¯
    0.09
    æij¸æ¸ħ
    0.09
    ç¡®å®ļ
    0.09
    æī¾åĩĨ
    0.08
    Activations Density 0.215%

    No Known Activations