© 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. 43320
    Prev
    Next
    INDEX
    Explanations

    season, writing

    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
    çħ
    -0.07
    ois
    -0.07
    ore
    -0.06
    engo
    -0.06
    hini
    -0.06
    çģĮ
    -0.06
    /latest
    -0.06
     inc
    -0.06
    oze
    -0.06
    çģ«èħ¿
    -0.06
    POSITIVE LOGITS
    ÙĤب
    0.08
    åľ°çĽĺ
    0.08
    æį®ä»ĭç»į
    0.08
    å¯Ĩæĸ¯
    0.08
    没帮åĬ©
    0.07
    igni
    0.07
    iences
    0.07
    转贴
    0.07
    å½±åŁİ
    0.07
    ersion
    0.07
    Activations Density 0.036%

    No Known Activations