© 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. 20840
    Prev
    Next
    INDEX
    Explanations

    images and graphics

    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
    .normalize
    -0.07
    hak
    -0.07
    åı£æ°Ķ
    -0.07
    綿
    -0.07
    olley
    -0.07
    éĶIJæĦıè¿Ľåıĸ
    -0.07
    chein
    -0.07
    é£İåIJ¹è¿ĩ
    -0.07
     outpost
    -0.07
    éĹ®åĮ»çĶŁ
    -0.06
    POSITIVE LOGITS
    visual
    0.12
     visuals
    0.12
     визÑĥ
    0.11
    缴è§Ĥ
    0.11
     visual
    0.11
    åĽ¾å½¢
    0.11
    /graph
    0.10
    è§Ĩè§ī
    0.10
     graphical
    0.10
    缴è§ĤçļĦ
    0.10
    Activations Density 0.428%

    No Known Activations