© 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. 12972
    Prev
    Next
    INDEX
    Explanations

    currently, prevalence, count

    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
    edm
    -0.07
    chter
    -0.07
    rico
    -0.07
     sep
    -0.07
    伪
    -0.07
     ep
    -0.07
    æĻ¤
    -0.07
    arz
    -0.06
    ếm
    -0.06
    mente
    -0.06
    POSITIVE LOGITS
    ersistent
    0.09
     temporarily
    0.08
    åŃĺéĩı
    0.08
    çŁŃæļĤçļĦ
    0.08
    _OW
    0.08
    çŁŃæļĤ
    0.08
    å½ĵæŶ
    0.08
    éĥ½æĺ¯ä»İ
    0.08
    Temporary
    0.08
    临æŶ
    0.08
    Activations Density 0.017%

    No Known Activations