© 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. 43484
    Prev
    Next
    INDEX
    Explanations

    is/are followed by adjectives or past participles

    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
    幸ç¦ıå¿«ä¹IJ
    -0.09
    æ°¸è¿ľçļĦ
    -0.08
    好好çļĦ
    -0.08
     Insg
    -0.08
     án
    -0.08
    å°±è¿Ļæł·
    -0.08
    amol
    -0.08
    alsy
    -0.08
    utzer
    -0.08
    *dt
    -0.08
    POSITIVE LOGITS
     crucial
    0.08
    G
    0.07
    p
    0.07
    P
    0.07
     considered
    0.07
    C
    0.06
    F
    0.06
    B
    0.06
    ps
    0.06
    è§Ĩ为
    0.06
    Activations Density 0.423%

    No Known Activations