© 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. 45208
    Prev
    Next
    INDEX
    Explanations

    star types

    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¸įæĪIJ
    -0.08
    หู
    -0.07
    erez
    -0.07
    ldata
    -0.07
    ropp
    -0.07
    æĹłå¤Ħ
    -0.07
    abin
    -0.07
    ibat
    -0.07
    qa
    -0.07
     Lazar
    -0.07
    POSITIVE LOGITS
    æ¯Ķèĩªå·±
    0.08
    å®ľå±ħ
    0.08
    ç»ĩ女
    0.07
     Classification
    0.07
     classification
    0.07
    åıijåħī
    0.07
    寿åij½
    0.07
    ÑĤип
    0.07
     Federation
    0.07
     Grill
    0.07
    Activations Density 0.024%

    No Known Activations