© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29883
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    äºĭå®ŀåĴĮ
    -0.09
    astia
    -0.08
    ç¾¹
    -0.07
    夾
    -0.07
    keh
    -0.07
    pch
    -0.06
    sii
    -0.06
    ({...
    -0.06
    anj
    -0.06
    åħ°çī¹
    -0.06
    POSITIVE LOGITS
    raits
    0.07
    æľĢç»Ī
    0.07
     reck
    0.07
    ÑĢиÑĤа
    0.07
     herz
    0.07
    åħ¬
    0.07
    æŃ£å¼ı
    0.06
    ieu
    0.06
    rada
    0.06
    Final
    0.06
    Activations Density 0.000%

    No Known Activations