© 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. 18540
    Prev
    Next
    INDEX
    Explanations

    text part 1 or 2

    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
    å±Ģ
    -0.07
    urt
    -0.07
     Pins
    -0.07
    ecas
    -0.06
    æĤī
    -0.06
    izion
    -0.06
    éder
    -0.06
    çļĦä¸Ģå¼ł
    -0.06
    é¸¡æ¯Ľ
    -0.06
    dic
    -0.06
    POSITIVE LOGITS
    argest
    0.08
     componente
    0.08
    £
    0.08
     componenti
    0.07
    è´¡çĮ®
    0.07
    åħ´
    0.07
    alin
    0.07
    aland
    0.07
    éĶ»
    0.07
     bezpoÅĽred
    0.07
    Activations Density 0.001%

    No Known Activations