© 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. 2897
    Prev
    Next
    INDEX
    Explanations

    positive evaluation or status

    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
    mium
    -0.08
    inals
    -0.07
    itmap
    -0.07
     appunto
    -0.07
    enko
    -0.07
    ught
    -0.07
    /ext
    -0.07
    ç¿»äºĨ
    -0.07
    åįģåħ¨
    -0.07
    以èĩ´
    -0.07
    POSITIVE LOGITS
    没éĹ®é¢ĺ
    0.08
    è¿Ļéĥ¨åĪĨ
    0.08
     straightforward
    0.08
    没æľīéĹ®é¢ĺ
    0.07
     Ø£Ùħا
    0.07
    accio
    0.07
    客
    0.07
    积
    0.07
    第ä¸Ģéĥ¨åĪĨ
    0.07
    .googleapis
    0.07
    Activations Density 0.200%

    No Known Activations