© 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. 2809
    Prev
    Next
    INDEX
    Explanations

    cyanobacteria and algae

    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
    ç¾Ķ
    -0.08
    çĸ²è½¯
    -0.07
    çĻ¾äºĭ
    -0.07
     capac
    -0.07
    æŁļ
    -0.07
    èĨ
    -0.06
    çĬ
    -0.06
    åľ°é»Ħ
    -0.06
    è±¹
    -0.06
     aard
    -0.06
    POSITIVE LOGITS
     algae
    0.10
    åħīåIJĪä½ľçĶ¨
    0.09
    èĹ»
    0.09
    æµ·èĹ»
    0.08
    æµĴ
    0.08
     colonies
    0.08
    åħ±çĶŁ
    0.08
    wnd
    0.07
    åľ¨éĺ³åħīä¸ĭ
    0.07
    SCO
    0.07
    Activations Density 0.029%

    No Known Activations