© 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. 20381
    Prev
    Next
    INDEX
    Explanations

    chromosomal aberrations

    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
    彦
    -0.07
    ãĥĤ
    -0.07
    }while
    -0.07
    MSG
    -0.07
    æľīè¯Ŀ
    -0.07
     Connected
    -0.07
    å°±æĺ¯æĪijçļĦ
    -0.07
    lify
    -0.06
    ä¸Ń磩
    -0.06
    ç¾İçĻ½
    -0.06
    POSITIVE LOGITS
    æĹłæ³ķæŃ£å¸¸
    0.10
    æIJºå¸¦
    0.08
     defective
    0.07
    ekar
    0.07
    åı¯å¯¼èĩ´
    0.07
    éĢłæĪIJäºĨ
    0.07
    æĶľ
    0.07
    æŃ£å¸¸çļĦ
    0.07
     malformed
    0.07
    iph
    0.07
    Activations Density 0.007%

    No Known Activations