© 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. 12377
    Prev
    Next
    INDEX
    Explanations

    causal execution

    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
    è¿ĶåĽŀåĪĹ表
    -0.10
    agni
    -0.08
    ä¸ĩæĸ¹
    -0.08
     angef
    -0.08
    deo
    -0.08
    llib
    -0.07
    ä»»ä½ķåªĴä½ĵ
    -0.07
    ãĥªãĥ¼ãĥĪ
    -0.07
    antung
    -0.07
    NotFoundError
    -0.07
    POSITIVE LOGITS
    oling
    0.08
     caus
    0.07
     faster
    0.07
    æıŃ
    0.07
    çľī
    0.07
     harmful
    0.07
    çĿ¹
    0.07
    åįķåIJij
    0.07
    çļĦåĪºæ¿Ģ
    0.07
    mata
    0.07
    Activations Density 0.004%

    No Known Activations