© 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. 31500
    Prev
    Next
    INDEX
    Explanations

    omycin, toxin, rapamycin

    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
    ä¸ĭçıŃ
    -0.07
    被æīĵ
    -0.07
     Bris
    -0.07
    vo
    -0.07
    rau
    -0.07
    çļĦéĩįè¦ģéĢĶå¾Ħ
    -0.07
    olv
    -0.06
    çĻ¾åº¦äºij
    -0.06
    褶
    -0.06
    ëĭ´
    -0.06
    POSITIVE LOGITS
     disrupt
    0.09
    edException
    0.08
    éĺ»æŃ¢
    0.08
     selectively
    0.08
     binds
    0.08
    аÑĤоÑĢа
    0.08
     disrupting
    0.08
    ycin
    0.08
    geld
    0.08
    æĹłæķĪ
    0.08
    Activations Density 0.238%

    No Known Activations