© 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. 10161
    Prev
    Next
    INDEX
    Explanations

    designed for use

    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
     ë¬¼ë¡ł
    -0.07
    öö
    -0.07
     dilanjutkan
    -0.07
    ateau
    -0.07
     ingres
    -0.07
    inium
    -0.07
    วà¸ģ
    -0.07
    à¹Ħà¸Ķà¹īà¸Ĺีà¹Ī
    -0.07
    缮åīįåľ¨
    -0.07
     majd
    -0.07
    POSITIVE LOGITS
     designed
    0.13
     Designed
    0.10
    Designed
    0.10
    -designed
    0.10
    çĶ¨æĿ¥
    0.09
    å°±æĺ¯ä¸ºäºĨ
    0.09
    çī¹å®ļçļĦ
    0.09
    ä¸ĵ为
    0.08
     expressly
    0.08
     conçu
    0.08
    Activations Density 0.309%

    No Known Activations