© 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. 64431
    Prev
    Next
    INDEX
    Explanations

    key points or details

    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
    ska
    -0.09
    AndView
    -0.08
    ysterious
    -0.08
    Deletes
    -0.07
    ingerprint
    -0.07
    èĭ¥å¹²éĹ®é¢ĺçļĦ解éĩĬ
    -0.07
    æĸ°éĹ»ç½ij
    -0.07
    ulton
    -0.07
    NewLabel
    -0.07
    à¹ģหà¹Īà¸ĩà¸Ļีà¹ī
    -0.07
    POSITIVE LOGITS
     about
    0.09
     regarding
    0.09
    point
    0.08
     bahwa
    0.08
    以ä¸ĭåĩłçĤ¹
    0.07
    åħ³äºİ
    0.07
     concernant
    0.07
    åĦ¿
    0.07
    ìĤ¬íķŃ
    0.07
     tentang
    0.07
    Activations Density 0.018%

    No Known Activations