© 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. 22207
    Prev
    Next
    INDEX
    Explanations

    anodic aluminum oxide layer

    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
     collider
    -0.07
    ç´§å¼łçļĦ
    -0.07
    æŀī
    -0.07
    涤纶
    -0.07
    è°IJ
    -0.06
    çĻ½éĵ¶
    -0.06
    clair
    -0.06
    phant
    -0.06
     movers
    -0.06
    æķĸ
    -0.06
    POSITIVE LOGITS
    ä¿ĿæĬ¤èĨľ
    0.10
     protective
    0.10
    å±ĤçļĦ
    0.10
    å±Ĥ
    0.10
     layer
    0.10
    ä¸Ģå±Ĥ
    0.10
    ä¿ĿæĬ¤å±Ĥ
    0.10
     layers
    0.09
    Layers
    0.09
     заÑīиÑĤ
    0.09
    Activations Density 0.014%

    No Known Activations