© 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. 25197
    Prev
    Next
    INDEX
    Explanations

    grocery input

    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
    祺
    -0.07
    天ä»Ļ
    -0.06
    å¸IJåı·
    -0.06
    è¯ģåĪ¸äº¤æĺĵæīĢ
    -0.06
    (cont
    -0.06
    asa
    -0.06
    енÑĮ
    -0.06
    áĥ¬áĥ§
    -0.06
     rè
    -0.06
    ãĤ½ãĥ¼
    -0.06
    POSITIVE LOGITS
    ugier
    0.08
     пÑĢид
    0.08
    ivic
    0.07
    裾
    0.07
    .statusText
    0.07
    upan
    0.07
    å¤ķ
    0.06
    mbH
    0.06
    ussi
    0.06
    象
    0.06
    Activations Density 0.006%

    No Known Activations