© 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. 20181
    Prev
    Next
    INDEX
    Explanations

    temperature and cryogenics

    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
     Gres
    -0.08
    vro
    -0.08
    æĢħ
    -0.08
    ebol
    -0.08
    ç¦ħ
    -0.08
    åī¯çIJĨäºĭéķ¿
    -0.08
    æ¯ı天éĥ½ä¼ļ
    -0.07
    åģĩ
    -0.07
    utan
    -0.07
    hra
    -0.07
    POSITIVE LOGITS
     cold
    0.08
    åĨ·
    0.08
    cold
    0.08
    Cold
    0.08
    åĨ·çļĦ
    0.08
     Cold
    0.07
    uard
    0.07
    æĭīå¾·
    0.07
    å³»
    0.07
    æݧåĪ¶åľ¨
    0.07
    Activations Density 0.007%

    No Known Activations