© 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. 43804
    Prev
    Next
    INDEX
    Explanations

    quote, estimate, information

    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
    onitor
    -0.08
     commenter
    -0.07
    ä¸Ģåį¡éĢļ
    -0.07
    é¦ĸåıij
    -0.07
     vigil
    -0.07
    indsight
    -0.07
    ä¹ĸ
    -0.07
    çĶ¨æĪ·ä½¿çĶ¨
    -0.07
    社ä¼ļæ²»çIJĨ
    -0.07
     AUTOR
    -0.07
    POSITIVE LOGITS
    æĦıåIJij
    0.11
    åĪĿæŃ¥
    0.10
     prospective
    0.10
    åı¯è¡ĮæĢ§
    0.10
     confidential
    0.09
    æ´½è°Ī
    0.09
     unverbind
    0.09
    æ½ľåľ¨å®¢æĪ·
    0.09
    好æĦŁ
    0.09
    è¯ķ驾
    0.09
    Activations Density 0.619%

    No Known Activations